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

    Neuronpedia

    INDEX
    Explanations

    Varied text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colomb
    -0.07
    (li
    -0.07
    .?
    -0.07
    字幕
    -0.06
     یاد
    -0.06
     evaluation
    -0.06
     MF
    -0.06
     COPY
    -0.06
     Tucker
    -0.06
     tn
    -0.06
    POSITIVE LOGITS
    fts
    0.06
     تح
    0.06
    PCODE
    0.06
    duk
    0.06
    _ra
    0.06
     generado
    0.06
     Вы
    0.06
    icas
    0.06
    izu
    0.06
    Incoming
    0.06
    Act Density 0.039%

    No Known Activations