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

    Neuronpedia

    INDEX
    Explanations

    language relating to self-worth and value

    oai_token-act-pair · gemini-2.0-flash

    Self-worth and self-esteem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
     виправивши
    -0.54
     ļ
    -0.52
    Климат
    -0.48
     comuniques
    -0.48
    それも
    -0.46
    '})
    -0.45
    ')),
    -0.44
     lontano
    -0.44
     '/')
    -0.44
    POSITIVE LOGITS
    parsedMessage
    0.81
     MotionEvent
    0.73
     समीक्षाओं
    0.68
     createSprite
    0.68
    EDEFAULT
    0.66
    MethodManager
    0.65
    Personensuche
    0.62
    HomeAsUpEnabled
    0.61
    inghouse
    0.60
    脚注の使い方
    0.59
    Act Density 0.982%

    No Known Activations