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

    Neuronpedia

    INDEX
    Explanations

    versatility, corporatism, hermeticism, copilot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.13
    ق
    1.13
    in
    1.04
    ع
    1.04
    to
    0.98
    ви
    0.98
    та
    0.98
    t
    0.93
    an
    0.93
    ين
    0.93
    POSITIVE LOGITS
    )
    0.63
    、
    0.63
    ช่วง
    0.62
     второй
    0.58
    یده
    0.56
    加え
    0.56
    uted
    0.55
    )，
    0.54
    くて
    0.54
    くない
    0.53
    Act Density 0.311%

    No Known Activations