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

    Neuronpedia

    INDEX
    Explanations

    X itself is/are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sami
    1.11
     supplémentaires
    1.06
     zaidi
    1.04
    𝟐
    1.04
     demais
    1.03
    更多
    1.02
     именно
    1.00
     dalších
    1.00
    𝐬
    0.99
     více
    0.96
    POSITIVE LOGITS
     collapse
    0.89
     collapses
    0.86
     collapsed
    0.82
     cannot
    0.82
     token
    0.81
     incarnations
    0.81
     ceases
    0.81
    ök
    0.80
    fected
    0.79
     존재하는
    0.79
    Act Density 0.180%

    No Known Activations