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

    Neuronpedia

    INDEX
    Explanations

    conscientiousness and assembly .bss sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.93
    ق
    0.86
    ש
    0.85
    ن
    0.80
    د
    0.80
     on
    0.75
    א
    0.74
    س
    0.74
    자
    0.73
    ج
    0.72
    POSITIVE LOGITS
    cję
    0.78
    hamdulillah
    0.76
    Ane
    0.71
     mogę
    0.68
    Shang
    0.66
     нәрсә
    0.66
    inį
    0.65
    hrung
    0.65
    Failure
    0.64
    Jähr
    0.64
    Act Density 0.001%

    No Known Activations