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

    Neuronpedia

    INDEX
    Explanations

    information in various languages related to conditions, inquiries, and descriptive phrases

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

    Non-English words or code snippets

    np_acts-logits-general · gemini-2.0-flash

    technical commands and error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.86
     Monfieur
    -0.79
     becauſe
    -0.78
     Theſe
    -0.77
     ſhe
    -0.76
     whoſe
    -0.75
     myſelf
    -0.74
     houſe
    -0.74
     raiſ
    -0.74
     themſelves
    -0.74
    POSITIVE LOGITS
    ]+=
    0.42
    بوابة
    0.41
     cielos
    0.40
     virksom
    0.40
    Buyers
    0.39
     confronti
    0.39
     Rowling
    0.36
    soka
    0.35
     výstav
    0.35
    fortawesome
    0.34
    Act Density 0.058%

    No Known Activations