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

    Neuronpedia

    INDEX
    Explanations

    elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cling
    -0.07
    utdown
    -0.07
     Forest
    -0.06
    Vertical
    -0.06
    儿
    -0.06
    iage
    -0.06
     FTC
    -0.06
    ilo
    -0.06
     medication
    -0.06
    ATED
    -0.06
    POSITIVE LOGITS
    .serialize
    0.07
     clubhouse
    0.07
    	Task
    0.07
    .assertNot
    0.07
    (Stack
    0.07
    ующ
    0.06
    getNode
    0.06
    	tp
    0.06
     UNS
    0.06
     itir
    0.06
    Act Density 0.034%

    No Known Activations