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

    Neuronpedia

    INDEX
    Explanations

    terms related to the process of revising or repeating actions or concepts

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

    starting with "re" followed by a vowel

    np_acts-logits-general · gemini-2.0-flash

    actions repeated or revised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.48
     Abonnez
    -0.47
    ArgsConstructor
    -0.44
    IUrlHelper
    -0.43
    autaire
    -0.42
     considérons
    -0.42
     dům
    -0.42
    GLint
    -0.42
    getMinutes
    -0.41
    vician
    -0.41
    POSITIVE LOGITS
     re
    0.77
     Re
    0.63
    postsleuth
    0.60
     rebuilding
    0.57
    Re
    0.57
     Rebuild
    0.56
     rebuild
    0.55
     पुन
    0.55
     Rebirth
    0.52
     rein
    0.51
    Act Density 0.362%

    No Known Activations