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

    Neuronpedia

    INDEX
    Explanations

    quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للد
    -0.06
     deber
    -0.06
    _redis
    -0.06
     oils
    -0.06
     realiza
    -0.06
    Loads
    -0.06
     гор
    -0.06
     endiş
    -0.06
     nga
    -0.06
     Güven
    -0.06
    POSITIVE LOGITS
    _external
    0.09
     traditions
    0.08
    address
    0.07
    像是
    0.07
    .utc
    0.07
     Fraction
    0.07
    window
    0.07
    ersed
    0.06
    .override
    0.06
     glitches
    0.06
    Act Density 0.002%

    No Known Activations