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

    Neuronpedia

    INDEX
    Explanations

    _ASSIGN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _subtitle
    -0.06
    арамет
    -0.06
    eč
    -0.06
    PCODE
    -0.06
    /foo
    -0.06
    .Handle
    -0.06
     improved
    -0.06
    arket
    -0.06
     solving
    -0.06
    cas
    -0.06
    POSITIVE LOGITS
     marrying
    0.06
    _sites
    0.06
    rang
    0.06
    意思
    0.06
    =>$
    0.06
    (depth
    0.06
    crast
    0.06
    	Config
    0.06
    masked
    0.06
    lenir
    0.06
    Act Density 0.001%

    No Known Activations