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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     первой
    -0.08
    .BUTTON
    -0.08
     بهذا
    -0.08
    命题
    -0.07
     promoting
    -0.07
    meta
    -0.07
    ErrorResponse
    -0.07
    买单
    -0.07
     prv
    -0.07
     summarized
    -0.07
    POSITIVE LOGITS
    chester
    0.08
    در
    0.07
    泚
    0.06
    جن
    0.06
    cité
    0.06
     Glass
    0.06
    cial
    0.06
    sse
    0.06
    シー
    0.06
    Iterable
    0.06
    Act Density 0.001%

    No Known Activations