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

    Neuronpedia

    INDEX
    Explanations

    new opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.90
    2
    0.87
    يل
    0.80
    sproz
    0.76
    time
    0.74
     opportunity
    0.72
    '
    0.68
    m
    0.68
    opportunity
    0.66
    να
    0.63
    POSITIVE LOGITS
    竰
    0.78
    ظیم
    0.75
    ۹
    0.75
    ない
    0.73
    0.72
     REGIUNI
    0.72
     Opportunities
    0.71
    ių
    0.71
    ン
    0.71
    Ⴖ
    0.71
    Act Density 0.005%

    No Known Activations