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

    Neuronpedia

    INDEX
    Explanations

    degree or amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可能性
    0.73
    拥有
    0.70
    ផុត
    0.68
     eignet
    0.65
    擁有
    0.63
     എന്നീ
    0.63
     اتصال
    0.63
     произошло
    0.61
    ቻል
    0.61
     Schönheit
    0.61
    POSITIVE LOGITS
     minimal
    1.26
     negligible
    1.23
     lessened
    1.18
     extensive
    1.17
     limited
    1.17
     plentiful
    1.15
     paramount
    1.14
     varied
    1.13
     minimized
    1.12
     nonexistent
    1.11
    Act Density 0.806%

    No Known Activations