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

    Neuronpedia

    INDEX
    Explanations

    problem descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $filter
    -0.07
    _public
    -0.07
     협
    -0.06
    (EIF
    -0.06
    .templates
    -0.06
     oči
    -0.06
    adiator
    -0.06
    ylvania
    -0.06
    ULE
    -0.06
    افر
    -0.06
    POSITIVE LOGITS
     Profiles
    0.07
    .faces
    0.06
    _increase
    0.06
    .coord
    0.06
     deriving
    0.06
     weighted
    0.06
     Lum
    0.06
    roach
    0.06
     lum
    0.06
     FontWeight
    0.06
    Act Density 0.069%

    No Known Activations