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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gloss
    -0.07
    uffles
    -0.07
     intending
    -0.07
     hesitate
    -0.06
     readonly
    -0.06
    ()));
    -0.06
     JAXBElement
    -0.06
     junge
    -0.06
     hedef
    -0.06
     hasNext
    -0.06
    POSITIVE LOGITS
    قية
    0.07
    PageIndex
    0.06
    好了
    0.06
     plunged
    0.06
     borderTop
    0.06
    ,o
    0.06
     právo
    0.06
    통
    0.06
    .Live
    0.06
     THANK
    0.06
    Act Density 0.005%

    No Known Activations