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

    Neuronpedia

    INDEX
    Explanations

    Bitcoin/coin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ersive
    -0.07
    onesia
    -0.07
     females
    -0.07
     Pill
    -0.07
     genome
    -0.06
     Atmospheric
    -0.06
    	Entity
    -0.06
     inclu
    -0.06
    mae
    -0.06
    Este
    -0.06
    POSITIVE LOGITS
    ='.$
    0.08
    avn
    0.07
     |\
    0.07
    vron
    0.06
    AutoresizingMask
    0.06
     рабоч
    0.06
     JO
    0.06
    ßer
    0.06
    �
    0.06
     skips
    0.06
    Act Density 0.006%

    No Known Activations