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

    Neuronpedia

    INDEX
    Explanations

    statistics and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    これで
    1.52
     apical
    1.51
    क्ट
    1.23
     blatantly
    1.21
     stator
    1.16
     variety
    1.16
    ই
    1.14
     substantially
    1.11
     pronounced
    1.10
    j
    1.10
    POSITIVE LOGITS
     guter
    1.67
     ThemeData
    1.53
     Nome
    1.48
    に
    1.47
     пройти
    1.46
    ب
    1.45
    ের
    1.45
     eTo
    1.45
     quinto
    1.43
    로
    1.43
    Act Density 0.099%

    No Known Activations