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

    Neuronpedia

    INDEX
    Explanations

    access to resources or justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.83
     كل
    0.82
    لي
    0.78
     غير
    0.77
     سي
    0.76
     في
    0.76
     مي
    0.75
    يك
    0.73
    ودة
    0.73
    وري
    0.73
    POSITIVE LOGITS
    a
    1.17
    to
    1.15
    on
    1.07
    ه
    0.94
    ↵↵
    0.93
    u
    0.93
    i
    0.93
    d
    0.90
     Access
    0.89
     was
    0.88
    Act Density 0.051%

    No Known Activations