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

    Neuronpedia

    INDEX
    Explanations

    access to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    劵
    0.46
     ガス
    0.44
    yati
    0.39
    ncols
    0.37
    ガス
    0.37
    隅
    0.35
    牵
    0.35
     कपास
    0.35
    鬘
    0.34
    ۤ
    0.33
    POSITIVE LOGITS
    iversity
    0.36
    Tokenizer
    0.35
    gender
    0.33
    cled
    0.33
    ingredient
    0.33
     Министерство
    0.32
    uri
    0.32
    operative
    0.32
    тин
    0.31
     લઈને
    0.31
    Act Density 0.005%

    No Known Activations