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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     τα
    -0.07
     BMI
    -0.06
    profiles
    -0.06
    ="#
    -0.06
    .Private
    -0.06
     burada
    -0.06
     chilling
    -0.06
    .News
    -0.06
     darker
    -0.06
    .toolStrip
    -0.06
    POSITIVE LOGITS
    —
    0.07
    agos
    0.07
    $page
    0.06
     sécur
    0.06
     Discussion
    0.06
    swana
    0.06
     vigor
    0.06
    (indent
    0.06
              ↵
    0.06
    $stmt
    0.06
    Act Density 0.047%

    No Known Activations