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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RA
    -0.07
    .reshape
    -0.07
     swear
    -0.07
    .OutputStream
    -0.07
     cancers
    -0.07
    "These
    -0.07
    \xe
    -0.07
    �
    -0.07
     Hurricanes
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Когда
    0.07
    bounded
    0.07
     когда
    0.07
    ,tmp
    0.06
    Line
    0.06
     expres
    0.06
     ngắn
    0.06
     polarity
    0.06
    淺
    0.06
    FIX
    0.06
    Act Density 0.028%

    No Known Activations