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

    Neuronpedia

    INDEX
    Explanations

    discovery mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     întâ
    0.49
     superiores
    0.48
    .
    0.48
    0.46
     riječ
    0.45
     Núñez
    0.45
     cabeça
    0.44
     copiar
    0.44
    ógrafo
    0.44
     esquina
    0.43
    POSITIVE LOGITS
    PID
    0.43
     kanssa
    0.43
     impurities
    0.42
    CAST
    0.41
    璘
    0.41
    KI
    0.41
     impurity
    0.41
    TAR
    0.41
    TES
    0.40
    ปรุง
    0.40
    Act Density 0.005%

    No Known Activations