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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handicap
    -0.07
    oltage
    -0.07
    松
    -0.06
     waves
    -0.06
    wc
    -0.06
     begged
    -0.06
     Mac
    -0.06
    	return
    -0.06
    Working
    -0.06
    heels
    -0.06
    POSITIVE LOGITS
     mainAxisAlignment
    0.07
     straightforward
    0.07
    INIT
    0.06
    :invoke
    0.06
     chance
    0.06
    -thinking
    0.06
     rtl
    0.06
    senha
    0.06
    ीम
    0.06
    .ACCESS
    0.06
    Act Density 0.052%

    No Known Activations