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

    Neuronpedia

    INDEX
    Explanations

    approximately

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     တို့
    0.52
     خفی
    0.49
    ᐉ
    0.48
     څنګه
    0.48
    引き続き
    0.48
     گرفتن
    0.47
    здат
    0.46
    መር
    0.46
    种种
    0.46
    چھے
    0.46
    POSITIVE LOGITS
     approximately
    3.31
     около
    3.20
     around
    3.13
     sekitar
    3.11
    約
    3.02
     حوالي
    2.98
     aproximadamente
    2.86
     około
    2.86
     approx
    2.84
    approximately
    2.84
    Act Density 0.777%

    No Known Activations