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

    Neuronpedia

    INDEX
    Explanations

    offend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MOV
    -0.08
     Forecast
    -0.07
     Init
    -0.07
    з
    -0.07
    _signup
    -0.07
     Hazard
    -0.07
    .ru
    -0.07
    ivalent
    -0.06
     с
    -0.06
     Prevention
    -0.06
    POSITIVE LOGITS
    ActionBar
    0.07
    .XtraLayout
    0.07
     offended
    0.07
    miyor
    0.06
     angered
    0.06
    iii
    0.06
     offend
    0.06
     dễ
    0.06
     ensuring
    0.06
    ekte
    0.06
    Act Density 0.019%

    No Known Activations