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

    Neuronpedia

    INDEX
    Explanations

    Therefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arg
    0.76
     siz
    0.76
     Infer
    0.75
    逾
    0.73
     restit
    0.72
     attest
    0.71
     angl
    0.70
     Choices
    0.70
     Taylor
    0.70
     Sistem
    0.69
    POSITIVE LOGITS
    So
    1.03
    Therefore
    0.88
    therefore
    0.77
    Sometimes
    0.77
    लोर
    0.75
    Especially
    0.74
    GitHub
    0.73
    Scroll
    0.73
    witch
    0.72
    ゴ
    0.70
    Act Density 0.080%

    No Known Activations