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

    Neuronpedia

    INDEX
    Explanations

    Courtesy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mouth
    -0.07
    Ｖ
    -0.06
    郴州
    -0.06
    隼
    -0.06
     numéro
    -0.06
    _province
    -0.06
    enter
    -0.06
    =./
    -0.06
    _checked
    -0.06
    °
    -0.06
    POSITIVE LOGITS
    гранич
    0.07
    Priv
    0.07
     stabil
    0.07
     mathematic
    0.07
     matériel
    0.07
    (None
    0.07
     lib
    0.07
     quy
    0.06
     eğitim
    0.06
     scores
    0.06
    Act Density 0.003%

    No Known Activations