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

    Neuronpedia

    INDEX
    Explanations

    personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Partners
    -0.07
    _GREEN
    -0.07
    提交
    -0.07
     guiding
    -0.07
     Girl
    -0.07
     Gazette
    -0.07
     Honey
    -0.07
     Mate
    -0.07
     Master
    -0.07
    ывал
    -0.07
    POSITIVE LOGITS
    	cp
    0.06
     elect
    0.06
     dejtings
    0.06
     PropTypes
    0.06
    .clf
    0.06
    ransition
    0.06
     μπορεί
    0.06
    \
↵
    0.06
    isinde
    0.06
     NEGLIGENCE
    0.06
    Act Density 0.066%

    No Known Activations