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

    Neuronpedia

    INDEX
    Explanations

    Technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {}_
    -0.07
     forensic
    -0.07
    _XDECREF
    -0.06
    competition
    -0.06
    \helpers
    -0.06
    .full
    -0.06
    és
    -0.06
    šen
    -0.06
    obel
    -0.06
     Πα
    -0.06
    POSITIVE LOGITS
     M
    0.07
    display
    0.07
    		↵	↵
    0.06
     setColor
    0.06
    M
    0.06
    ____________
    0.06
    =D
    0.06
     首
    0.06
    	className
    0.06
     bst
    0.06
    Act Density 0.000%

    No Known Activations