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

    Neuronpedia

    INDEX
    Explanations

    logical host, unit, resource, component, grouping, set or category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ولكن
    0.64
     غير
    0.63
    P
    0.61
    Eff
    0.58
    ،
    0.58
    auce
    0.57
     ކ
    0.57
     ذریعے
    0.57
     be
    0.56
     pháp
    0.56
    POSITIVE LOGITS
     logical
    0.96
    ר
    0.93
    ת
    0.93
    ა
    0.92
    ing
    0.90
    ب
    0.79
    ना
    0.75
    ar
    0.74
    ل
    0.72
     embankment
    0.71
    Act Density 0.005%

    No Known Activations