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

    Neuronpedia

    INDEX
    Explanations

    requests for help and assistance

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

    Sentences asking for help or feedback

    np_acts-logits-general · gemini-2.0-flash

    asking for any help or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.70
    FieldBuilder
    -0.56
     akong
    -0.53
    ָׁ
    -0.50
    onViewCreated
    -0.49
    featureID
    -0.49
     setAddress
    -0.47
    webElementXpaths
    -0.47
    Lähteet
    -0.47
    iress
    -0.47
    POSITIVE LOGITS
     welcome
    0.72
     orice
    0.69
     ANY
    0.69
    Any
    0.68
     anything
    0.67
    Anything
    0.66
     Cualquier
    0.65
     help
    0.65
     Anything
    0.65
     any
    0.65
    Act Density 0.189%

    No Known Activations