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

    Neuronpedia

    INDEX
    Explanations

    Hanuman, Monkey King, Ramayana

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ام
    0.90
    ब्ल्यू
    0.80
    و
    0.80
    ون
    0.77
    ח
    0.73
    ak
    0.72
    ج
    0.72
    ophytes
    0.71
    א
    0.71
    ب
    0.70
    POSITIVE LOGITS
     हनुमान
    0.71
     Hanuman
    0.68
     Ram
    0.63
    Progress
    0.63
     बॉलीवुड
    0.61
     предстоя
    0.60
    Compress
    0.59
     hairst
    0.59
     beper
    0.59
     wor
    0.56
    Act Density 0.002%

    No Known Activations