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

    Neuronpedia

    INDEX
    Explanations

    PONE journal reference ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    id
    -0.07
    wk
    -0.07
    gv
    -0.07
    ़ा
    -0.06
    .VERTICAL
    -0.06
     teal
    -0.06
    湿
    -0.06
     설
    -0.06
    nge
    -0.06
     vomiting
    -0.06
    POSITIVE LOGITS
     Prompt
    0.07
     Armed
    0.07
    Wunused
    0.06
    (char
    0.06
    министра
    0.06
    .*/↵
    0.06
     ******************************************************************************/↵
    0.06
     Reduce
    0.06
    	es
    0.06
    )){
↵
    0.06
    Act Density 0.039%

    No Known Activations