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

    Neuronpedia

    INDEX
    Explanations

    Social media comments/logins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quadratic
    -0.07
     方
    -0.07
    党
    -0.07
    <input
    -0.06
     팀
    -0.06
     debug
    -0.06
    修改
    -0.06
    (=
    -0.06
    [Z
    -0.06
    -compatible
    -0.06
    POSITIVE LOGITS
    Slinky
    0.07
     stringBy
    0.06
    ,function
    0.06
     mü
    0.06
    ферен
    0.06
     accur
    0.05
     обст
    0.05
    iversit
    0.05
    тобы
    0.05
     interim
    0.05
    Act Density 0.002%

    No Known Activations