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

    Neuronpedia

    INDEX
    Explanations

    places and associated terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ryl
    0.98
    ueto
    0.97
    banam
    0.96
     jotka
    0.93
     kembali
    0.92
     symmetries
    0.91
    ury
    0.86
     festgestellt
    0.86
    3
    0.86
     Lobkovic
    0.85
    POSITIVE LOGITS
    h
    1.30
     utterly
    0.95
    한
    0.85
     In
    0.85
     т
    0.85
    した
    0.84
     һ
    0.84
    си
    0.84
    ন
    0.82
    ह
    0.82
    Act Density 0.001%

    No Known Activations