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

    Neuronpedia

    INDEX
    Explanations

    a plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੱਚ
    0.49
    zev
    0.48
    nor
    0.48
     Zukunft
    0.47
    addEnemy
    0.46
     Angeb
    0.46
    ныгы
    0.46
    𝙣
    0.46
    кновен
    0.46
    zeni
    0.45
    POSITIVE LOGITS
     unimaginable
    0.48
     MAN
    0.47
    ET
    0.46
     Gastro
    0.46
     Soak
    0.46
     Cardio
    0.45
    ETTE
    0.45
     Gaia
    0.44
     selfless
    0.44
     CAN
    0.44
    Act Density 0.000%

    No Known Activations