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

    Neuronpedia

    INDEX
    Explanations

    Project, payment, can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .}(
    0.84
    annten
    0.80
     CELLS
    0.74
    राष्ट्रीय
    0.73
    arına
    0.73
    пка
    0.72
    UMENTS
    0.71
    syringe
    0.70
    lare
    0.70
     препарат
    0.68
    POSITIVE LOGITS
    ipation
    0.87
    acial
    0.77
     Jumat
    0.77
     kahe
    0.72
    inery
    0.70
    caster
    0.70
     cancellation
    0.70
     saan
    0.70
     졸
    0.69
    ერი
    0.68
    Act Density 0.001%

    No Known Activations