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

    Neuronpedia

    INDEX
    Explanations

    objects and disposal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поми
    0.40
     visitors
    0.39
     réfé
    0.37
     stimul
    0.37
    visitors
    0.37
     ды
    0.36
     pengunjung
    0.36
     sbagli
    0.36
     دستاویز
    0.36
    机票
    0.35
    POSITIVE LOGITS
    疃
    0.47
    ياة
    0.43
    Roy
    0.42
     जानकारी
    0.41
    敚
    0.39
    Infos
    0.38
     Roy
    0.38
    بعض
    0.38
    little
    0.38
    Jax
    0.38
    Act Density 0.000%

    No Known Activations