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

    Neuronpedia

    INDEX
    Explanations

    closing curly brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Uniwers
    0.99
     destinat
    0.92
     δημο
    0.91
     ప్రముఖ
    0.89
     Dispatch
    0.89
     Пу
    0.86
     نموذج
    0.86
    linewidth
    0.86
    系の
    0.86
    这部
    0.86
    POSITIVE LOGITS
     else
    0.66
    ായ്
    0.62
     leap
    0.62
    ions
    0.60
     shifts
    0.57
    ngModel
    0.56
    strual
    0.55
     पाह
    0.55
    NG
    0.55
     say
    0.55
    Act Density 0.244%

    No Known Activations