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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    域
    -0.07
    625
    -0.07
     вероят
    -0.07
     malfunction
    -0.06
    eras
    -0.06
    alty
    -0.06
     us
    -0.06
     arriv
    -0.06
    чает
    -0.06
     maté
    -0.06
    POSITIVE LOGITS
     موسیقی
    0.08
    (comment
    0.07
     QVERIFY
    0.07
    	GL
    0.07
     │
    0.06
    Ngh
    0.06
     uvědom
    0.06
    洲
    0.06
     受
    0.06
     CHE
    0.06
    Act Density 0.006%

    No Known Activations