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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     空
    -0.07
    EW
    -0.07
    343
    -0.07
    -block
    -0.07
     distress
    -0.06
     dementia
    -0.06
    (PC
    -0.06
    Raw
    -0.06
    规定
    -0.06
    -_
    -0.06
    POSITIVE LOGITS
     Hayden
    0.07
    �
    0.07
    .mContext
    0.06
    文学
    0.06
    .TEXT
    0.06
     Railroad
    0.06
    kee
    0.06
    mf
    0.06
     lexer
    0.06
    his
    0.06
    Act Density 0.014%

    No Known Activations