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

    Neuronpedia

    INDEX
    Explanations

    .html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utton
    -0.07
    urvey
    -0.06
     italic
    -0.06
     jm
    -0.06
     metabolism
    -0.06
     首页
    -0.06
     saturated
    -0.06
    	cp
    -0.06
     illusion
    -0.06
    nota
    -0.06
    POSITIVE LOGITS
    /account
    0.07
    exit
    0.07
    connection
    0.06
    .con
    0.06
    tí
    0.06
     Mul
    0.06
    .tem
    0.06
     divide
    0.06
    FIG
    0.06
    .al
    0.06
    Act Density 0.043%

    No Known Activations