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

    Neuronpedia

    INDEX
    Explanations

    power

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _For
    -0.07
     mouths
    -0.07
    -selection
    -0.06
     arch
    -0.06
     Locations
    -0.06
     نو
    -0.06
     buys
    -0.06
    \">↵
    -0.06
     lows
    -0.06
    	m
    -0.06
    POSITIVE LOGITS
     Chili
    0.07
     Power
    0.07
    ataka
    0.07
     resume
    0.06
     powering
    0.06
    ounsel
    0.06
     Lemon
    0.06
     Muscle
    0.06
    قم
    0.06
     радян
    0.06
    Act Density 0.019%

    No Known Activations