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

    Neuronpedia

    INDEX
    Explanations

    dependence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Events
    -0.07
     tail
    -0.07
     veut
    -0.07
     Tf
    -0.07
     bum
    -0.06
    _rate
    -0.06
    _dead
    -0.06
    據
    -0.06
     मद
    -0.06
    GW
    -0.06
    POSITIVE LOGITS
    remen
    0.06
    TERN
    0.06
     aup
    0.06
    ์ช
    0.06
    -з
    0.06
     Ferguson
    0.06
    �다
    0.06
    一覧
    0.06
    ruz
    0.06
    اف
    0.06
    Act Density 0.110%

    No Known Activations