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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ımız
    -0.08
     stability
    -0.07
     tastes
    -0.07
    事业
    -0.07
     pests
    -0.07
    usters
    -0.07
     aspirations
    -0.07
    .st
    -0.07
    oves
    -0.06
    𝐅
    -0.06
    POSITIVE LOGITS
    쿄
    0.08
    Appending
    0.07
     relate
    0.07
     neuronal
    0.07
     chance
    0.07
    ᨸ
    0.06
     الدنيا
    0.06
     LU
    0.06
    חוו
    0.06
    FUNC
    0.06
    Act Density 0.045%

    No Known Activations