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

    Neuronpedia

    INDEX
    Explanations

    strong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fé
    -0.07
     zby
    -0.06
    tti
    -0.06
    -DD
    -0.06
    ยม
    -0.06
    owl
    -0.06
    .'/'.$
    -0.06
    getWidth
    -0.06
    uations
    -0.06
    ique
    -0.06
    POSITIVE LOGITS
    recogn
    0.07
    Trait
    0.07
    ционных
    0.07
     refunds
    0.06
    (push
    0.06
    uvian
    0.06
    Boston
    0.06
    ))?
    0.06
     belki
    0.06
    Strong
    0.06
    Act Density 0.002%

    No Known Activations