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
    lug
    -0.07
    _pet
    -0.07
     willen
    -0.07
    pot
    -0.06
    ider
    -0.06
    Ｌ
    -0.06
    .cast
    -0.06
    ιλ
    -0.06
     flown
    -0.06
    halb
    -0.06
    POSITIVE LOGITS
    .fromRGBO
    0.07
     servants
    0.07
     Osc
    0.07
     đế
    0.06
     Mc
    0.06
    	printk
    0.06
    Marco
    0.06
     jugador
    0.06
    центра
    0.06
     prestige
    0.06
    Act Density 0.004%

    No Known Activations