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

    Neuronpedia

    INDEX
    Explanations

    negative consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frivol
    -0.07
     μπ
    -0.06
     сло
    -0.06
     investigator
    -0.06
    änn
    -0.06
     OA
    -0.06
    :@"
    -0.06
     reven
    -0.06
     reconstruct
    -0.06
     durable
    -0.06
    POSITIVE LOGITS
    ोड़
    0.07
    appen
    0.06
    akk
    0.06
     下跌
    0.06
    amız
    0.06
    uddle
    0.06
     kak
    0.06
    .fillStyle
    0.06
    /yyyy
    0.06
    SError
    0.06
    Act Density 0.014%

    No Known Activations