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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    унд
    -0.07
     label
    -0.07
    _CONST
    -0.07
    록
    -0.07
    _look
    -0.06
    .Bean
    -0.06
    чного
    -0.06
    peats
    -0.06
    (headers
    -0.05
    -black
    -0.05
    POSITIVE LOGITS
    》↵
    0.08
    skill
    0.07
     println
    0.06
     Rogue
    0.06
    agu
    0.06
    	super
    0.06
    .shift
    0.06
     články
    0.06
     마
    0.06
    shuffle
    0.06
    Act Density 0.002%

    No Known Activations