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

    Neuronpedia

    INDEX
    Explanations

    Quesadillas, Peanut, metal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ires
    0.44
     carbides
    0.42
    篓
    0.39
    ''(
    0.38
    '+
    0.38
    ITERATURE
    0.38
    avk
    0.37
    그리고
    0.37
    glasses
    0.37
    copies
    0.37
    POSITIVE LOGITS
     byla
    0.46
     Chapter
    0.44
     ήταν
    0.44
     Universität
    0.44
     Behavioral
    0.44
     статьи
    0.44
    Escolhido
    0.43
     Professor
    0.43
     qued
    0.43
     Artikel
    0.43
    Act Density 0.012%

    No Known Activations