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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tasks
    -0.07
    80
    -0.07
    Elements
    -0.07
    钟
    -0.07
     psychiat
    -0.07
    icals
    -0.07
    Element
    -0.06
     gesch
    -0.06
    _SANITIZE
    -0.06
     Latest
    -0.06
    POSITIVE LOGITS
    .BL
    0.07
    @Slf
    0.06
    меж
    0.06
     geom
    0.06
     شهید
    0.06
    music
    0.06
    $filter
    0.06
     aka
    0.06
     agreg
    0.06
     वजह
    0.05
    Act Density 0.006%

    No Known Activations