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

    Neuronpedia

    INDEX
    Explanations

    translations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hmm
    -0.09
     somehow
    -0.08
     inutile
    -0.08
     Hmm
    -0.08
     coder
    -0.08
     useless
    -0.08
     mediocre
    -0.08
    ???↵
    -0.08
     dull
    -0.07
     Another
    -0.07
    POSITIVE LOGITS
     officially
    0.12
     oficialmente
    0.11
    <|endoftext|>
    0.11
     официаль
    0.11
    。截至
    0.11
     officiellement
    0.10
    <|reserved_200016|>
    0.10
     offiziell
    0.10
     ofic
    0.10
    ，截至
    0.09
    Act Density 0.125%

    No Known Activations