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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twist
    -0.06
     tz
    -0.06
    21
    -0.06
     Hat
    -0.06
     crane
    -0.06
     Sphere
    -0.06
     Curt
    -0.06
     секрет
    -0.06
     Catherine
    -0.06
    	l
    -0.06
    POSITIVE LOGITS
     nějak
    0.07
    .labelControl
    0.07
    ्रश
    0.06
    _failed
    0.06
     {@
    0.06
     breakpoints
    0.06
     제가
    0.06
    /plain
    0.06
     administrators
    0.06
    غير
    0.06
    Act Density 0.027%

    No Known Activations