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

    Neuronpedia

    INDEX
    Explanations

    symmetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miners
    -0.09
    (userid
    -0.09
     depleted
    -0.08
    くだ
    -0.08
     chronique
    -0.08
     permettront
    -0.08
     জর
    -0.08
     personnalis
    -0.08
     sabab
    -0.08
    _alert
    -0.08
    POSITIVE LOGITS
     symmetry
    0.19
     symmetrical
    0.14
     symmetric
    0.11
     вращ
    0.10
     sym
    0.10
    -axis
    0.10
    sym
    0.09
     folding
    0.09
     axis
    0.09
    transpose
    0.09
    Act Density 0.027%

    No Known Activations