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

    Neuronpedia

    INDEX
    Explanations

    plotting and alerts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Resource
    0.83
     international
    0.76
     International
    0.76
     informed
    0.73
    Resource
    0.72
    resource
    0.72
     resource
    0.70
     pictures
    0.68
     Inform
    0.67
     Active
    0.67
    POSITIVE LOGITS
    mySocket
    0.72
     कैंसिल
    0.70
    ㄙ
    0.68
    ชี
    0.66
    玷
    0.65
     раздра
    0.65
    crum
    0.64
    ждения
    0.64
     прийма
    0.64
     madison
    0.63
    Act Density 0.005%

    No Known Activations