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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uo
    -0.07
     Andrew
    -0.07
    gin
    -0.07
    »
    -0.06
     ejected
    -0.06
     plainly
    -0.06
    .Formatter
    -0.06
     ”↵
    -0.06
    	gui
    -0.06
     genome
    -0.06
    POSITIVE LOGITS
    _IF
    0.07
    (descriptor
    0.07
     نتایج
    0.07
    ewn
    0.07
     може
    0.06
     başlay
    0.06
    ]==
    0.06
    には
    0.06
    dealloc
    0.06
    щі
    0.06
    Act Density 0.248%

    No Known Activations