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

    Neuronpedia

    INDEX
    Explanations

    named or other word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    šel
    0.80
    ports
    0.80
    する
    0.79
    atives
    0.79
    ite
    0.77
    itin
    0.76
     VAT
    0.76
    зан
    0.76
    ises
    0.74
    ibles
    0.73
    POSITIVE LOGITS
    ิ
    1.09
    э
    1.04
    ی
    1.02
     admittedly
    0.98
    耋
    0.95
    т
    0.92
     sweaty
    0.91
     crowded
    0.91
     shelved
    0.90
     emoz
    0.90
    Act Density 0.000%

    No Known Activations