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

    Neuronpedia

    INDEX
    Explanations

    specific token sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ev
    0.47
    chmal
    0.46
    provides
    0.46
     once
    0.45
    zol
    0.44
    norm
    0.44
     provides
    0.44
    '}
    0.43
     sekali
    0.41
    p
    0.41
    POSITIVE LOGITS
    ిత
    0.46
    흑
    0.43
    trashItem
    0.43
     Spirituality
    0.42
    উদ্
    0.42
    학과
    0.41
    Makefile
    0.40
    граф
    0.40
     spirituality
    0.40
     supersymmetry
    0.40
    Act Density 0.003%

    No Known Activations