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

    Neuronpedia

    INDEX
    Explanations

    fclose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _invite
    -0.07
    	exec
    -0.07
    遨
    -0.07
     IDb
    -0.07
     Fixture
    -0.07
    iera
    -0.07
     Neon
    -0.06
     useMemo
    -0.06
    zzle
    -0.06
     Consumers
    -0.06
    POSITIVE LOGITS
    enthal
    0.07
     palabra
    0.07
    𝇚
    0.07
     Бр
    0.07
     الدفاع
    0.07
     والا
    0.07
    грам
    0.07
     Dum
    0.07
    .Connection
    0.07
    霜
    0.07
    Act Density 0.002%

    No Known Activations