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

    Neuronpedia

    INDEX
    Explanations

    words related to inspiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺰ
    1.88
    ज
    1.82
    ﺮ
    1.82
    #######
    1.79
    ンの
    1.78
    t
    1.77
    ﻮ
    1.72
    Gracias
    1.68
    כ
    1.68
    з
    1.66
    POSITIVE LOGITS
    氇
    2.13
     necessari
    1.91
     uniquement
    1.88
     dichiarato
    1.88
     milites
    1.86
     defam
    1.84
     quidem
    1.83
     microseconds
    1.83
     visant
    1.82
    volle
    1.77
    Act Density 0.006%

    No Known Activations