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

    Neuronpedia

    INDEX
    Explanations

    Advanced topics and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lə
    1.79
    ্লাহ
    1.66
    ം
    1.66
    นะคะ
    1.62
    יות
    1.59
    ième
    1.53
    də
    1.53
    λια
    1.53
    ర్
    1.52
    션
    1.52
    POSITIVE LOGITS
    س
    2.17
    ile
    2.09
    are
    1.90
    ോ
    1.84
    ado
    1.80
    and
    1.78
    する
    1.77
    お
    1.77
    ions
    1.76
    ato
    1.74
    Act Density 0.020%

    No Known Activations