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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ant
    -0.07
     KAR
    -0.07
     panor
    -0.06
    .Est
    -0.06
    Icon
    -0.06
    剑
    -0.06
    .Stack
    -0.06
    ISTS
    -0.06
    AFF
    -0.06
    <Book
    -0.06
    POSITIVE LOGITS
     Means
    0.07
    čas
    0.07
    ="↵
    0.07
     doesnt
    0.07
     مختلف
    0.06
     starttime
    0.06
     maxi
    0.06
     protected
    0.06
     Protected
    0.06
    auge
    0.06
    Act Density 0.064%

    No Known Activations