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

    Neuronpedia

    INDEX
    Explanations

    locations and governance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rujuakan
    -0.54
    الحياه
    -0.53
     SafeArea
    -0.50
     ligiloj
    -0.49
    Спољашње
    -0.48
    Abitanti
    -0.47
     링크
    -0.46
    SerializedSize
    -0.46
    principalColumn
    -0.45
    Hochspringen
    -0.45
    POSITIVE LOGITS
     gardens
    0.59
    dwell
    0.59
    gardens
    0.56
     gardening
    0.55
    出版年
    0.55
     fires
    0.54
     kids
    0.54
    يكب
    0.53
     guards
    0.52
    oneofs
    0.51
    Act Density 0.001%

    No Known Activations