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

    Neuronpedia

    INDEX
    Explanations

    decision making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有利于
    1.54
    ﻟ
    1.51
    有助于
    1.49
    が多く
    1.46
    を用意
    1.44
    有一定的
    1.43
     educativos
    1.42
    خدم
    1.41
    Fees
    1.41
    ET
    1.40
    POSITIVE LOGITS
    g
    2.59
    v
    2.03
    gning
    1.94
    us
    1.90
    ام
    1.89
    ли
    1.88
    gruppen
    1.82
    د
    1.80
    dır
    1.80
    es
    1.76
    Act Density 0.098%

    No Known Activations