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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dd
    -0.08
     lipstick
    -0.07
     �
    -0.07
    чні
    -0.07
    odus
    -0.07
     گذاری
    -0.07
    fts
    -0.06
    �로
    -0.06
    mise
    -0.06
    ディア
    -0.06
    POSITIVE LOGITS
     mutableListOf
    0.07
    	ERROR
    0.07
    <Vec
    0.07
     Alphabet
    0.06
     spend
    0.06
     kitap
    0.06
    …ط
    0.06
     textbooks
    0.06
     Flow
    0.06
    (run
    0.06
    Act Density 0.006%

    No Known Activations