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

    Neuronpedia

    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Foundation
    -0.07
     and
    -0.06
    �
    -0.06
    Warnings
    -0.06
    ront
    -0.06
    μαν
    -0.06
     negligible
    -0.06
     campus
    -0.06
    Mir
    -0.06
    ensity
    -0.06
    POSITIVE LOGITS
     monster
    0.07
    阪
    0.06
     oğlu
    0.06
    (PHP
    0.06
    тик
    0.06
    	file
    0.06
     ต
    0.06
     başlat
    0.06
    ồm
    0.06
    ト
    0.06
    Act Density 0.008%

    No Known Activations