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

    Neuronpedia

    INDEX
    Explanations

    Social media engagement metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    기가
    -0.07
    	My
    -0.06
     Association
    -0.06
    Different
    -0.06
     Daddy
    -0.06
    เหม
    -0.06
     Legs
    -0.06
    orque
    -0.06
     Par
    -0.06
     Lean
    -0.06
    POSITIVE LOGITS
    їв
    0.06
     tý
    0.06
     sailors
    0.06
     чес
    0.06
     �
    0.06
     xmm
    0.06
     UClass
    0.06
    webkit
    0.06
    _SANITIZE
    0.06
    initWith
    0.06
    Act Density 0.017%

    No Known Activations