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

    Neuronpedia

    INDEX
    Explanations

    disable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivist
    -0.07
     pork
    -0.07
    rito
    -0.07
    ucid
    -0.07
    níkem
    -0.07
     borrowed
    -0.06
    kor
    -0.06
     paramString
    -0.06
    xford
    -0.06
     Records
    -0.06
    POSITIVE LOGITS
    ジュ
    0.07
     Pg
    0.06
     sailing
    0.06
    two
    0.06
     Scot
    0.06
    -collapse
    0.06
    _setting
    0.06
    the
    0.06
    -blind
    0.06
     MEMBER
    0.06
    Act Density 0.023%

    No Known Activations