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

    Neuronpedia

    INDEX
    Explanations

    tbsp Butter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MyRegisterClass
    0.45
    dyž
    0.42
     ആര
    0.42
    emore
    0.41
    ாலத்தில்
    0.40
    ounc
    0.39
     fick
    0.39
    ಾನ
    0.39
    miri
    0.38
    derd
    0.38
    POSITIVE LOGITS
     deploy
    0.43
     cosidd
    0.43
    はこの
    0.43
     estratégico
    0.42
    서비스
    0.39
    ڍ
    0.39
    ческую
    0.39
     servizio
    0.39
     busiest
    0.38
    بعة
    0.38
    Act Density 0.005%

    No Known Activations