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

    Neuronpedia

    INDEX
    Explanations

    cucharadita, wohlbefinden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    1.95
    c
    1.85
    ak
    1.73
    ou
    1.71
    ap
    1.62
    ab
    1.55
    ก
    1.50
    op
    1.48
    w
    1.46
    ent
    1.44
    POSITIVE LOGITS
    {
    2.06
    ۵
    1.45
    ==
    1.42
    5
    1.40
    ५
    1.39
    ని
    1.31
    لة
    1.29
    4
    1.29
    До
    1.27
    ৫
    1.27
    Act Density 0.414%

    No Known Activations