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

    Neuronpedia

    INDEX
    Explanations

    parentheses/semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonuç
    -0.07
     kø
    -0.06
     füh
    -0.06
    -----------↵↵
    -0.06
     Holdings
    -0.06
    裝
    -0.06
     helpless
    -0.06
     parsing
    -0.06
     pazar
    -0.06
     traverse
    -0.06
    POSITIVE LOGITS
    quant
    0.07
    Soft
    0.07
    	bg
    0.07
    iesz
    0.07
    řes
    0.06
    .sym
    0.06
    Ga
    0.06
    -events
    0.06
    setDisplay
    0.06
    (mat
    0.06
    Act Density 0.047%

    No Known Activations