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

    Neuronpedia

    INDEX
    Explanations

    Code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     metal
    -0.06
    _ALERT
    -0.06
     bảng
    -0.06
     /[
    -0.06
    _TABLE
    -0.06
    iel
    -0.06
    -cols
    -0.06
     glEnd
    -0.06
     Dish
    -0.06
     филь
    -0.06
    POSITIVE LOGITS
    عن
    0.07
     datings
    0.07
    结合
    0.07
     تحلیل
    0.06
    ilitation
    0.06
     Sitting
    0.06
    _gate
    0.06
    ADX
    0.06
    いや
    0.06
    IBILITY
    0.06
    Act Density 0.025%

    No Known Activations