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

    Neuronpedia

    INDEX
    Explanations

    data retrieval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itzer
    -0.07
    RAD
    -0.06
    回头看
    -0.06
    彗
    -0.06
    翡翠
    -0.06
     Card
    -0.06
    _passwd
    -0.06
     Spar
    -0.06
    鲢
    -0.06
    愛
    -0.06
    POSITIVE LOGITS
    Voltage
    0.08
    	address
    0.07
     Reaction
    0.07
    ecurity
    0.07
     rockets
    0.07
    เทคโนโลย
    0.06
    쥴
    0.06
     şirket
    0.06
    HU
    0.06
     Float
    0.06
    Act Density 0.020%

    No Known Activations