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

    Neuronpedia

    INDEX
    Explanations

    technical/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.97
    hyrchwyd
    -0.78
    BeginContext
    -0.69
    SharedDtor
    -0.63
    ViewImports
    -0.63
    ">:
    -0.62
    #
    -0.60
     ligiloj
    -0.58
    \{\\
    -0.58
    NOP
    -0.58
    POSITIVE LOGITS
    diğ
    0.50
    ViewFeatures
    0.45
     Capitan
    0.40
     saites
    0.39
    TagMode
    0.39
    Introducing
    0.38
     heavy
    0.37
     Großen
    0.36
     střed
    0.36
    ługi
    0.36
    Act Density 0.005%

    No Known Activations