Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    positive descriptors and superlative terms referring to the quality or status of items or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive reviews or descriptions

    np_acts-logits-general · gemini-2.0-flash

    positive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.50
     فريبيس
    -0.49
    verifyException
    -0.49
    ChildIndex
    -0.43
    Източници
    -0.43
     assinatura
    -0.42
     подска
    -0.42
     quelconque
    -0.42
    Jîn
    -0.42
     cérebro
    -0.41
    POSITIVE LOGITS
     elegant
    0.56
    Gorgeous
    0.54
     незавершена
    0.54
     gorgeous
    0.53
     beautifully
    0.53
    Lovely
    0.53
     lovely
    0.53
     beautiful
    0.52
     Lovely
    0.52
    Stylish
    0.52
    Act Density 0.378%

    No Known Activations