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

    Neuronpedia

    INDEX
    Explanations

    public speaking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (des
    -0.08
     Ike
    -0.07
     France
    -0.07
     Superman
    -0.07
    <count
    -0.06
     أو
    -0.06
     ride
    -0.06
     будет
    -0.06
     scouting
    -0.06
    3
    -0.06
    POSITIVE LOGITS
     »↵↵
    0.07
     ев
    0.07
    	area
    0.06
     :",
    0.06
     terminated
    0.06
    剑
    0.06
    .typ
    0.06
    (params
    0.06
     Clin
    0.06
     useMemo
    0.06
    Act Density 0.079%

    No Known Activations