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

    Neuronpedia

    INDEX
    Explanations

    ============

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?s
    -0.06
    -dominated
    -0.06
    >Last
    -0.06
     huge
    -0.06
    Reuters
    -0.06
     ingresar
    -0.06
     equitable
    -0.06
    율
    -0.06
     Hurricanes
    -0.06
    amt
    -0.06
    POSITIVE LOGITS
    bc
    0.07
    BM
    0.06
     fi
    0.06
    822
    0.06
    .guna
    0.06
    呈
    0.06
    bef
    0.06
    [i
    0.06
    di
    0.06
    .glide
    0.06
    Act Density 0.001%

    No Known Activations