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

    Neuronpedia

    INDEX
    Explanations

    instances of code comments and specific code structure patterns

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

    projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CRI
    -0.44
    natur
    -0.39
    Ӕ
    -0.38
    AndEndTag
    -0.38
    alg
    -0.38
     hvert
    -0.35
    botten
    -0.35
    応
    -0.35
    opard
    -0.35
    styrelsen
    -0.35
    POSITIVE LOGITS
     progetti
    1.45
     projets
    0.95
     للاسماء
    0.76
     proyectos
    0.74
     projects
    0.72
     Projekte
    0.70
     projekty
    0.69
     PROJECTS
    0.67
     Projects
    0.66
     projet
    0.66
    Act Density 0.001%

    No Known Activations