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

    Neuronpedia

    INDEX
    Explanations

    random

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	div
    -0.07
     Zah
    -0.06
     Arab
    -0.06
     biểu
    -0.06
     juice
    -0.06
     woke
    -0.06
     positive
    -0.06
    _decode
    -0.06
     DATE
    -0.06
     přím
    -0.06
    POSITIVE LOGITS
    ()."
    0.07
     muht
    0.07
    .Many
    0.06
    ,W
    0.06
    /W
    0.06
    ,'
    0.06
     pthread
    0.06
    .out
    0.06
    …but
    0.06
    /stretchr
    0.06
    Act Density 0.005%

    No Known Activations