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

    Neuronpedia

    INDEX
    Explanations

    package names and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Smiley
    0.84
    කු
    0.80
     qRT
    0.73
     Juice
    0.72
    listBox
    0.72
     الماء
    0.71
    ֜
    0.71
    נ
    0.71
     ọ
    0.70
    ută
    0.69
    POSITIVE LOGITS
    \.
    0.85
    ::
    0.82
    .<
    0.78
    ravariant
    0.77
    .`
    0.76
     namespace
    0.76
     organization
    0.72
     সরকারের
    0.70
    ভিশ
    0.70
     사람들
    0.67
    Act Density 0.109%

    No Known Activations