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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chords
    -0.07
    	glUniform
    -0.07
     rewriting
    -0.07
     Handlers
    -0.06
     Erectile
    -0.06
    资料
    -0.06
     cyan
    -0.06
    ’Brien
    -0.06
    _mappings
    -0.06
     Reliable
    -0.06
    POSITIVE LOGITS
    aqu
    0.07
     Unique
    0.07
    िं
    0.07
     dissip
    0.06
     outfile
    0.06
     unique
    0.06
    万元
    0.06
     Venture
    0.06
    NU
    0.06
     ';↵
    0.06
    Act Density 0.018%

    No Known Activations