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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qtt
    -0.07
     maxValue
    -0.07
    .Find
    -0.07
    _but
    -0.07
    izr
    -0.06
    _OD
    -0.06
    #ac
    -0.06
    .router
    -0.06
    Think
    -0.06
    duk
    -0.06
    POSITIVE LOGITS
    amazon
    0.08
     anti
    0.08
    scient
    0.07
    饮
    0.06
    ΣΤ
    0.06
     Vị
    0.06
     Amount
    0.06
    Denver
    0.06
     ł
    0.06
     weak
    0.06
    Act Density 0.001%

    No Known Activations