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

    Neuronpedia

    INDEX
    Explanations

    library catalog listings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cias
    -0.08
    曰
    -0.08
     면
    -0.07
    typedef
    -0.07
     priz
    -0.07
    axi
    -0.07
     famiglia
    -0.07
     immobili
    -0.07
    matrix
    -0.07
    input
    -0.07
    POSITIVE LOGITS
     conflicts
    0.09
     संघर्ष
    0.08
     dinosaur
    0.08
     Thumb
    0.08
     поведения
    0.07
     konflik
    0.07
     Konfl
    0.07
     falls
    0.07
    冲
    0.07
     begeleiden
    0.07
    Act Density 0.002%

    No Known Activations