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

    Neuronpedia

    INDEX
    Explanations

    specific types or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ወቅት
    0.82
     mã
    0.80
    CODE
    0.74
     TIMESTAMP
    0.73
     مرور
    0.73
    μό
    0.72
     visu
    0.72
    ví
    0.72
    oresis
    0.71
    ㅂ
    0.71
    POSITIVE LOGITS
    ATIVES
    0.79
    aglia
    0.76
     भैया
    0.70
     हिर
    0.69
     جیسا
    0.69
    atives
    0.68
     कनेक्टिव
    0.68
    '$\
    0.67
    Energ
    0.66
     entendido
    0.66
    Act Density 0.000%

    No Known Activations