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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     области
    -0.07
     Isaac
    -0.06
    бора
    -0.06
     seminal
    -0.06
     lul
    -0.06
    .performance
    -0.06
    نجليزية
    -0.06
     ocur
    -0.06
     )->
    -0.06
    Expires
    -0.06
    POSITIVE LOGITS
     appearance
    0.07
     style
    0.06
     today
    0.06
     naked
    0.06
     substances
    0.06
    	style
    0.06
     pol
    0.06
     phrases
    0.06
    柱
    0.06
     signs
    0.06
    Act Density 0.000%

    No Known Activations