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

    Neuronpedia

    INDEX
    Explanations

    sections of code that involve user interactions and programming instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets containing file paths

    np_acts-logits-general · gemini-2.0-flash

    in [noun/context]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.66
    ArrowToggle
    -0.65
    reactstrap
    -0.60
    AnchorStyles
    -0.58
    IntoConstraints
    -0.55
    DockStyle
    -0.53
     numerus
    -0.53
     setuptools
    -0.51
     Walkover
    -0.49
    CJK
    -0.49
    POSITIVE LOGITS
    esai
    0.67
    يكب
    0.64
    іга
    0.60
    مقاله
    0.59
     Smarter
    0.57
     Вікі
    0.56
     hindsight
    0.56
    reise
    0.55
    wyk
    0.55
     ISOL
    0.54
    Act Density 0.421%

    No Known Activations