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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mes
    -0.07
    route
    -0.07
    �
    -0.06
    347
    -0.06
    ubuntu
    -0.06
     admits
    -0.06
    oru
    -0.06
    Currently
    -0.06
    essor
    -0.06
    bdd
    -0.06
    POSITIVE LOGITS
     přitom
    0.08
     Tập
    0.08
    (duration
    0.06
    .VisibleIndex
    0.06
    .general
    0.06
     Helvetica
    0.06
    $txt
    0.06
     puzzles
    0.06
    终于
    0.06
    lob
    0.06
    Act Density 0.006%

    No Known Activations