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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xiety
    -0.07
    ็จ
    -0.07
     Seit
    -0.06
    (obs
    -0.06
     šest
    -0.06
    	conf
    -0.06
    -front
    -0.06
     κατά
    -0.06
    _TextChanged
    -0.06
     власти
    -0.06
    POSITIVE LOGITS
     tribute
    0.09
     salute
    0.07
    firebase
    0.07
     honoring
    0.06
    ={({
    0.06
     Tribute
    0.06
    -positive
    0.06
     equals
    0.06
     правильно
    0.06
    .Variable
    0.06
    Act Density 0.014%

    No Known Activations