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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ps
    -0.07
    Detection
    -0.07
     secondary
    -0.07
     punishments
    -0.07
    +(
    -0.07
     Host
    -0.07
    Trial
    -0.07
    ？↵↵
    -0.07
    _json
    -0.07
     skeleton
    -0.07
    POSITIVE LOGITS
     zvlášt
    0.07
     ANC
    0.06
    _INITIALIZ
    0.06
     giành
    0.06
     دم
    0.06
    HE
    0.06
    τωση
    0.06
     Федераль
    0.06
    出现
    0.06
     النظام
    0.06
    Act Density 0.017%

    No Known Activations