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

    Neuronpedia

    INDEX
    Explanations

    time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     batch
    -0.07
     Public
    -0.06
    ーチ
    -0.06
    ETS
    -0.06
     Current
    -0.06
     pledge
    -0.06
    -cor
    -0.06
    (str
    -0.06
    ZZ
    -0.06
     lifespan
    -0.06
    POSITIVE LOGITS
    .')
    0.07
    าล
    0.07
    oused
    0.06
    jí
    0.06
    .newaxis
    0.06
    bildung
    0.06
    iyan
    0.06
    ipsis
    0.06
    개의
    0.06
     -->↵↵
    0.06
    Act Density 0.092%

    No Known Activations