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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lança
    -0.09
    $username
    -0.07
    뭄
    -0.07
    (selected
    -0.07
    rename
    -0.07
    ambah
    -0.07
    their
    -0.07
     Update
    -0.07
    aincontri
    -0.07
     Besides
    -0.07
    POSITIVE LOGITS
    ISTS
    0.07
     משת
    0.07
     jsx
    0.07
    .Push
    0.07
     metaph
    0.07
     definite
    0.07
    _FP
    0.06
    生产生活
    0.06
     bardzo
    0.06
    結合
    0.06
    Act Density 0.023%

    No Known Activations