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

    Neuronpedia

    INDEX
    Explanations

    rules and restrictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تلاش
    0.39
     equilibr
    0.36
     renderEncoder
    0.35
    考生
    0.35
     symbolically
    0.35
    ைகிறது
    0.34
    工作中
    0.33
    ชา
    0.32
    ìn
    0.32
     outperforms
    0.32
    POSITIVE LOGITS
     rules
    2.00
    rules
    1.73
     regulations
    1.73
     правила
    1.70
     reglas
    1.69
     laws
    1.67
     Rules
    1.66
     règles
    1.64
    规则
    1.62
     regole
    1.62
    Act Density 0.085%

    No Known Activations