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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assist
    -0.07
    ened
    -0.06
    较
    -0.06
    ^{
    -0.06
     governmental
    -0.06
    �
    -0.06
    .getTitle
    -0.06
    ルの
    -0.06
    užel
    -0.06
    ()}↵
    -0.06
    POSITIVE LOGITS
    /em
    0.07
     elegant
    0.07
    .country
    0.07
    perty
    0.06
     smtp
    0.06
    °E
    0.06
     dismissal
    0.06
    排
    0.06
    ::_('
    0.06
     boredom
    0.06
    Act Density 0.088%

    No Known Activations