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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hr
    -0.07
    лада
    -0.07
    characters
    -0.06
    -established
    -0.06
    /path
    -0.06
    овано
    -0.06
     interle
    -0.06
    lg
    -0.06
    ENCES
    -0.06
    trainer
    -0.06
    POSITIVE LOGITS
    ольно
    0.07
     barring
    0.06
     Degrees
    0.06
     wonders
    0.06
     intentional
    0.06
     Rocks
    0.06
     réseau
    0.06
     dando
    0.06
     Reyes
    0.06
    UID
    0.06
    Act Density 0.035%

    No Known Activations