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

    Neuronpedia

    INDEX
    Explanations

    action followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    1.17
     that
    1.14
     this
    1.06
     a
    0.95
     from
    0.94
     any
    0.93
     one
    0.90
     an
    0.88
     which
    0.88
     these
    0.87
    POSITIVE LOGITS
    drž
    0.67
    create
    0.65
     개발
    0.63
    创造
    0.62
    参加
    0.62
    ികിത്സ
    0.61
    任命
    0.61
    䬲
    0.61
    继续
    0.61
    provide
    0.61
    Act Density 0.002%

    No Known Activations