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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CppCodeGenWriteBarrier
    -0.07
     beside
    -0.07
    Mag
    -0.07
     Leaving
    -0.07
     smack
    -0.07
     него
    -0.07
     wide
    -0.07
    marsh
    -0.06
    aming
    -0.06
    矩阵
    -0.06
    POSITIVE LOGITS
     şirket
    0.07
    adera
    0.07
    _PERSON
    0.06
     длительн
    0.06
    ynchronously
    0.06
     fran
    0.06
    _MI
    0.06
    ⇉
    0.06
    -duration
    0.06
    쾌
    0.06
    Act Density 0.033%

    No Known Activations