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

    Neuronpedia

    INDEX
    Explanations

    News and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ver
    -0.08
     figured
    -0.07
     soát
    -0.06
    emaker
    -0.06
    CLAIM
    -0.06
    DEL
    -0.06
     управ
    -0.06
     Dahl
    -0.06
    STATE
    -0.05
    _quick
    -0.05
    POSITIVE LOGITS
    Slots
    0.07
    その他
    0.07
     bất
    0.06
     vaccination
    0.06
     hills
    0.06
     пож
    0.06
     v�
    0.06
    .***
    0.06
    vailability
    0.06
    .prevent
    0.06
    Act Density 0.180%

    No Known Activations