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

    Neuronpedia

    INDEX
    Explanations

    a word or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bars
    0.55
     cantilever
    0.54
     infarction
    0.54
     incumbent
    0.53
     ischemia
    0.52
     arbitration
    0.52
     regia
    0.52
     econometric
    0.51
     intoler
    0.50
     perempt
    0.50
    POSITIVE LOGITS
    ٔ
    0.50
    ，
    0.49
    布
    0.47
    耒
    0.45
    지
    0.45
    YPE
    0.45
    诛
    0.43
    Publisher
    0.43
    十二
    0.43
     ず
    0.43
    Act Density 0.000%

    No Known Activations