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

    Neuronpedia

    INDEX
    Explanations

    bloom filters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fon
    -0.07
    🍔
    -0.07
    ması
    -0.06
    -email
    -0.06
     Carlos
    -0.06
    nemonic
    -0.06
    面包
    -0.06
    eurs
    -0.06
    Abs
    -0.06
     Antonio
    -0.06
    POSITIVE LOGITS
    인이
    0.07
     wrongdoing
    0.07
     mingle
    0.07
     })();↵
    0.07
     ')';↵
    0.07
    addTo
    0.06
    _receipt
    0.06
    Sugar
    0.06
     reservations
    0.06
     "'
    0.06
    Act Density 0.002%

    No Known Activations