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

    Neuronpedia

    INDEX
    Explanations

    code import statements and System references

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.92
    rungsseite
    -0.91
    UnsafeEnabled
    -0.87
    featureID
    -0.84
    脚注の使い方
    -0.82
    Vidite
    -0.81
     '\\;'
    -0.79
    Personendaten
    -0.79
     مفص
    -0.75
    NUMX
    -0.75
    POSITIVE LOGITS
     ťaž
    0.57
     viszont
    0.44
     álla
    0.43
    cię
    0.43
    foria
    0.43
    AppCompatTheme
    0.42
     inoltre
    0.42
     &
    0.42
    menta
    0.41
     \&
    0.41
    Act Density 0.264%

    No Known Activations