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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax related to functions and parameters

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

    Code snippets with variable declarations

    np_acts-logits-general · gemini-2.0-flash

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Propri
    -0.52
     asynchronously
    -0.52
    propri
    -0.50
     charms
    -0.48
     rhinoceros
    -0.46
     branding
    -0.46
     Roper
    -0.46
    Bas
    -0.46
     Lob
    -0.45
    Lob
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.73
     candidats
    0.66
    RectangleBorder
    0.63
     algorit
    0.61
     تانيه
    0.60
     écoulé
    0.58
    LookAnd
    0.58
     preliminar
    0.58
     Majefty
    0.58
     chré
    0.57
    Act Density 0.487%

    No Known Activations