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

    Neuronpedia

    INDEX
    Explanations

    medical anecdotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crusher
    -0.07
    .gui
    -0.07
    れる
    -0.07
    -manager
    -0.07
    ESP
    -0.07
    (pred
    -0.06
     inspector
    -0.06
    Attach
    -0.06
    akt
    -0.06
     reviews
    -0.06
    POSITIVE LOGITS
    天堂
    0.06
    冒
    0.06
    getStatusCode
    0.06
     Пом
    0.06
    toFixed
    0.06
    010
    0.06
    走
    0.06
     vazgeç
    0.06
    也不
    0.06
    elleicht
    0.06
    Act Density 0.045%

    No Known Activations