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

    Neuronpedia

    INDEX
    Explanations

    Mathematical coefficients, 'c'

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chr
    -0.07
    iado
    -0.07
    afari
    -0.07
    xsd
    -0.06
    орту
    -0.06
     preferences
    -0.06
     �
    -0.06
     deaf
    -0.06
    紀
    -0.06
    kontakte
    -0.06
    POSITIVE LOGITS
    地下
    0.06
     nie
    0.06
    )"
    0.06
     ethnicity
    0.06
     Detail
    0.06
     직
    0.06
    張
    0.06
     Further
    0.06
     favored
    0.06
     O
    0.06
    Act Density 0.012%

    No Known Activations