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

    Neuronpedia

    INDEX
    Explanations

    identity or classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feliz
    0.44
     Aucun
    0.43
     resuspended
    0.43
    윅
    0.42
    queda
    0.42
     felices
    0.41
    кугӀ
    0.41
     fechas
    0.40
     Cliquez
    0.40
    <unused70>
    0.39
    POSITIVE LOGITS
    Software
    0.43
     Software
    0.40
     Env
    0.39
    Governance
    0.38
    BIN
    0.37
    Env
    0.37
    Conversion
    0.36
     DMV
    0.36
     broadening
    0.35
    making
    0.35
    Act Density 0.002%

    No Known Activations