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

    Neuronpedia

    INDEX
    Explanations

    distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     covariance
    -0.07
    chantment
    -0.07
     Adjust
    -0.07
    tingham
    -0.07
    рова
    -0.06
    ANTE
    -0.06
     mujer
    -0.06
    mployee
    -0.06
    .Con
    -0.06
    Persist
    -0.06
    POSITIVE LOGITS
     distribution
    0.08
    Distribution
    0.08
     Distribution
    0.08
     dire
    0.07
     distress
    0.06
    んど
    0.06
     someone
    0.06
    สาม
    0.06
    wrong
    0.06
     Kens
    0.06
    Act Density 0.001%

    No Known Activations