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

    Neuronpedia

    INDEX
    Explanations

    ul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    」。
    -0.07
     moss
    -0.07
    asta
    -0.07
    Close
    -0.07
    -colored
    -0.06
    uns
    -0.06
    arently
    -0.06
    .QLabel
    -0.06
     manifest
    -0.06
    	at
    -0.06
    POSITIVE LOGITS
    .contentOffset
    0.07
     包
    0.06
    .cmb
    0.06
     Treasure
    0.06
     OMG
    0.06
     gian
    0.06
     Fiat
    0.06
     thorough
    0.06
     BIO
    0.06
     kor
    0.06
    Act Density 0.005%

    No Known Activations