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

    Neuronpedia

    INDEX
    Explanations

    expertise and skill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.42
    변경된
    0.39
     खोज
    0.38
     Biblioteca
    0.37
     Universidade
    0.36
    乸
    0.36
     pubblic
    0.36
    無い
    0.36
    Biblioteca
    0.36
     Uit
    0.35
    POSITIVE LOGITS
    x
    0.52
    ol
    0.50
    r
    0.48
    ;
    0.48
    ,
    0.46
    ad
    0.46
    m
    0.45
    ir
    0.41
    w
    0.40
     delimiters
    0.39
    Act Density 0.290%

    No Known Activations