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

    Neuronpedia

    INDEX
    Explanations

    event target value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acce
    0.81
    ズノ
    0.78
    KZ
    0.77
    钰
    0.73
    ዔ
    0.73
     addButton
    0.73
    యన్
    0.72
    দ্দি
    0.72
     niên
    0.71
    पृ
    0.71
    POSITIVE LOGITS
    撬
    0.73
     soy
    0.70
     elsewhere
    0.70
     major
    0.69
    ровки
    0.69
    薜
    0.68
     always
    0.68
     AOL
    0.67
     Major
    0.66
     cesse
    0.66
    Act Density 0.001%

    No Known Activations