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

    Neuronpedia

    INDEX
    Explanations

    tension between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.88
    k
    0.84
    b
    0.79
    য়
    0.77
    kung
    0.76
    年の
    0.73
    uterine
    0.72
    ной
    0.72
    W
    0.71
    kungan
    0.71
    POSITIVE LOGITS
     människor
    0.74
    ({\
    0.68
    (-\
    0.64
     architectural
    0.64
    に含ま
    0.63
    อาจ
    0.62
    시킨
    0.62
    及
    0.62
     ori
    0.61
     особа
    0.61
    Act Density 0.000%

    No Known Activations