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

    Neuronpedia

    INDEX
    Explanations

    greek letters like mu, sigma, alpha

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тель
    2.02
    कर
    1.98
     nhiên
    1.83
    いた
    1.79
    𝟬
    1.76
    𝗳
    1.73
    𝔂
    1.73
    ু
    1.67
    까지
    1.65
    ។
    1.63
    POSITIVE LOGITS
     incidente
    2.14
    ES
    2.11
    trong
    2.11
    UR
    2.08
     vraie
    2.06
     avenir
    2.03
    ttes
    1.95
    ski
    1.95
    sby
    1.95
    siz
    1.94
    Act Density 0.110%

    No Known Activations