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

    Neuronpedia

    INDEX
    Explanations

    select radio buttons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kick
    0.45
     crush
    0.43
     hack
    0.43
     sun
    0.43
     gather
    0.43
     bring
    0.43
     pull
    0.43
     spille
    0.42
     curry
    0.42
     tok
    0.42
    POSITIVE LOGITS
    parametric
    0.48
    CONFLICT
    0.48
     दीजिए
    0.47
    پن
    0.47
    multicolumn
    0.47
    drugs
    0.47
    ת
    0.46
     मदद
    0.46
    تمد
    0.45
    degenerate
    0.45
    Act Density 0.000%

    No Known Activations