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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    かった
    -0.07
    Comp
    -0.06
    де
    -0.06
    특
    -0.06
    (Me
    -0.06
     Cancer
    -0.06
    lda
    -0.06
    horse
    -0.06
    _Man
    -0.06
     бла
    -0.06
    POSITIVE LOGITS
    .secondary
    0.07
    @pytest
    0.07
    _EXPECT
    0.06
    监听
    0.06
     parses
    0.06
    луш
    0.06
    альном
    0.06
     unused
    0.06
    afka
    0.06
     sentido
    0.06
    Act Density 0.024%

    No Known Activations