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

    Neuronpedia

    INDEX
    Explanations

    common or typical states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BES
    0.87
     coaction
    0.80
     inplace
    0.79
    aft
    0.78
     It
    0.78
    itet
    0.78
     peacock
    0.78
    agh
    0.78
    rived
    0.76
    oking
    0.76
    POSITIVE LOGITS
     تكون
    0.85
    グッズ
    0.80
     पैरों
    0.77
    ための
    0.75
    が多い
    0.74
     झालेल्या
    0.71
     يتم
    0.70
     कराने
    0.70
     يقوم
    0.70
     بيقول
    0.70
    Act Density 0.096%

    No Known Activations