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

    Neuronpedia

    INDEX
    Explanations

    AI safety disclaimers and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    visa
    0.46
    eco
    0.45
     visar
    0.45
     počíta
    0.44
     gunfire
    0.43
     allemaal
    0.42
     graves
    0.40
     kiosk
    0.40
     Presbyterian
    0.40
    很多的
    0.40
    POSITIVE LOGITS
    מש
    0.49
    د
    0.49
    _),
    0.48
    ار
    0.46
    ):
    0.46
    )*
    0.46
    ك
    0.45
    ل
    0.45
    ל
    0.44
     έχει
    0.44
    Act Density 0.003%

    No Known Activations