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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bildung
    -0.07
     AVL
    -0.07
    <boost
    -0.07
     Buffett
    -0.07
     Velvet
    -0.06
    ;")↵
    -0.06
    ічний
    -0.06
     inputFile
    -0.06
     songs
    -0.06
    JECTION
    -0.06
    POSITIVE LOGITS
    也是
    0.07
    ignment
    0.06
     Hint
    0.06
    PRE
    0.06
    ivors
    0.06
    ه
    0.06
    .closed
    0.06
    ier
    0.06
    умент
    0.06
    ≤
    0.06
    Act Density 0.015%

    No Known Activations