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

    Neuronpedia

    INDEX
    Explanations

    offense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ប
    -0.08
     wildlife
    -0.07
    엽
    -0.07
     getTime
    -0.07
    (Grid
    -0.07
     with
    -0.07
    ஜ
    -0.07
     الي
    -0.07
     banyak
    -0.06
    橫
    -0.06
    POSITIVE LOGITS
     tense
    0.08
     его
    0.07
    	fail
    0.07
     offense
    0.07
    _accum
    0.07
     PyErr
    0.07
     offence
    0.07
     fake
    0.07
    _ax
    0.07
     offenses
    0.07
    Act Density 0.004%

    No Known Activations