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

    Neuronpedia

    INDEX
    Explanations

    extraordinary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RH
    -0.08
     manten
    -0.07
    	lbl
    -0.07
    _vk
    -0.07
     görm
    -0.07
    消
    -0.07
     redundant
    -0.07
     refunded
    -0.07
    碧
    -0.07
    _pr
    -0.07
    POSITIVE LOGITS
    league
    0.07
    즑
    0.07
    精益
    0.07
    ряд
    0.07
     wagon
    0.07
     RegExp
    0.07
    )paren
    0.06
    Going
    0.06
    所在
    0.06
     FormControl
    0.06
    Act Density 0.003%

    No Known Activations