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

    Neuronpedia

    INDEX
    Explanations

    file type specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.78
    يروس
    0.73
    雰囲気
    0.72
    បែប
    0.71
    yl
    0.70
    ule
    0.69
     McG
    0.68
    ból
    0.68
    ેલ
    0.68
    रील
    0.68
    POSITIVE LOGITS
    ה
    0.82
     размере
    0.81
    নর
    0.76
    चलिए
    0.74
     Feminist
    0.74
     हिस्से
    0.72
     reasoned
    0.72
     দেবার
    0.71
    пута
    0.71
    меры
    0.70
    Act Density 0.004%

    No Known Activations