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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '',
    -0.07
    Conv
    -0.06
     ripe
    -0.06
    IVE
    -0.06
     tra
    -0.06
     Simpl
    -0.06
    Hon
    -0.06
     acre
    -0.06
     khẩu
    -0.06
    _corr
    -0.06
    POSITIVE LOGITS
    \uB
    0.07
    佳
    0.06
    owania
    0.06
    ontvangst
    0.06
    ินการ
    0.06
    孔
    0.06
    \Core
    0.06
    maal
    0.06
     ніч
    0.06
     Eternal
    0.06
    Act Density 0.003%

    No Known Activations