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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     коричне
    0.78
     Twentieth
    0.74
     nineteen
    0.74
     २०२
    0.74
     २०२२
    0.72
     Twenty
    0.71
     twentieth
    0.69
     Lighthouse
    0.68
    ومو
    0.68
    二十
    0.68
    POSITIVE LOGITS
     patru
    0.71
     hod
    0.59
    力が
    0.58
     व्याख्या
    0.58
    力
    0.57
     力
    0.56
    力を
    0.55
     nek
    0.55
    MPa
    0.54
     dining
    0.54
    Act Density 0.004%

    No Known Activations