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

    Neuronpedia

    INDEX
    Explanations

    Hudson River and inductive reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Asante
    0.36
    uminous
    0.36
    och
    0.34
     tịch
    0.34
    本地
    0.34
     போ
    0.33
    нев
    0.33
    rzej
    0.33
     Sidd
    0.32
     বাস
    0.32
    POSITIVE LOGITS
     valley
    0.43
    ჭ
    0.42
     particulière
    0.42
    推理
    0.41
    开心
    0.41
    зец
    0.40
    ளம்
    0.39
    ষধ
    0.39
    ଷ
    0.39
    ців
    0.38
    Act Density 0.003%

    No Known Activations