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

    Neuronpedia

    INDEX
    Explanations

    highlight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	connection
    -0.06
     kní
    -0.06
     AIR
    -0.06
    克斯
    -0.06
     случаев
    -0.06
    уванні
    -0.06
    _question
    -0.06
    ;?>↵
    -0.06
    しの
    -0.06
     establishes
    -0.06
    POSITIVE LOGITS
     highlights
    0.09
    IGHLIGHT
    0.07
    umeric
    0.07
     Highlights
    0.07
    Highlights
    0.07
    embr
    0.07
     clock
    0.06
    inky
    0.06
     delighted
    0.06
    Either
    0.06
    Act Density 0.006%

    No Known Activations