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

    Neuronpedia

    INDEX
    Explanations

    collected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reasons
    -0.08
    (Gravity
    -0.08
     فهم
    -0.07
     Chin
    -0.07
     myths
    -0.06
    _BODY
    -0.06
    BMI
    -0.06
     От
    -0.06
    _EXP
    -0.06
    .list
    -0.06
    POSITIVE LOGITS
    ประเภท
    0.07
    DECLARE
    0.06
    TickCount
    0.06
    likleri
    0.06
    cht
    0.06
    tik
    0.06
    корист
    0.06
     rebound
    0.06
    rowCount
    0.06
    ","","
    0.06
    Act Density 0.007%

    No Known Activations