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

    Neuronpedia

    INDEX
    Explanations

    pet adoption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apiro
    -0.07
    .fac
    -0.06
    adar
    -0.06
     carta
    -0.06
     nouvelles
    -0.06
    hawk
    -0.06
    cratch
    -0.06
    бира
    -0.06
    buch
    -0.06
    bart
    -0.06
    POSITIVE LOGITS
    (Action
    0.07
     Event
    0.06
     conscience
    0.06
    exit
    0.06
    =".$
    0.06
     authorised
    0.06
     unsubscribe
    0.06
    SpecWarn
    0.06
    (Render
    0.06
    .limit
    0.06
    Act Density 0.035%

    No Known Activations