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

    Neuronpedia

    INDEX
    Explanations

    say "20" numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADIUS
    -0.06
     vere
    -0.06
    .operator
    -0.06
     فراو
    -0.06
     tắt
    -0.06
    ,opt
    -0.06
    abei
    -0.06
     FUNCTIONS
    -0.06
    	audio
    -0.06
    _palette
    -0.06
    POSITIVE LOGITS
    _jButton
    0.07
    手を
    0.07
     plummet
    0.06
     �
    0.06
     nederland
    0.06
     muff
    0.06
     Positioned
    0.06
     hashtag
    0.06
    izzling
    0.06
    这是
    0.06
    Act Density 0.003%

    No Known Activations