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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >C
    -0.06
    /"+
    -0.06
    )=(
    -0.06
    azers
    -0.06
    (datetime
    -0.06
     mortal
    -0.06
    |R
    -0.06
    oload
    -0.06
    ﺔ
    -0.06
    ats
    -0.06
    POSITIVE LOGITS
     bribery
    0.08
    (Material
    0.07
     občan
    0.07
    Validity
    0.07
    -Series
    0.07
     clazz
    0.07
     algun
    0.07
     Roberto
    0.07
    _rx
    0.07
    (Op
    0.07
    Act Density 0.001%

    No Known Activations