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
    quee
    -0.07
    oil
    -0.07
     crises
    -0.07
    нен
    -0.06
     kiếm
    -0.06
    OLUMNS
    -0.06
     substring
    -0.06
     großen
    -0.06
     fodder
    -0.06
     adjacency
    -0.06
    POSITIVE LOGITS
    يكي
    0.07
    $output
    0.07
    ---@
    0.07
    sky
    0.06
     foreseeable
    0.06
     हट
    0.06
    (CG
    0.06
    -resource
    0.06
     الصف
    0.06
     examiner
    0.06
    Act Density 0.611%

    No Known Activations