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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flood
    -0.07
     dramas
    -0.07
    -scale
    -0.07
    BOARD
    -0.07
     Flood
    -0.07
     Turn
    -0.07
     newValue
    -0.07
     settle
    -0.07
    _toggle
    -0.06
     masks
    -0.06
    POSITIVE LOGITS
    	pr
    0.06
    ania
    0.06
     kode
    0.06
     Declaration
    0.06
    :'↵
    0.06
    ".$_
    0.06
    fuck
    0.05
    ='{$
    0.05
    lanması
    0.05
    	rb
    0.05
    Act Density 0.045%

    No Known Activations