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

    Neuronpedia

    INDEX
    Explanations

    acronyms and prefixes related to technology and science

    oai_token-act-pair · gemini-2.0-flash

    programming terms or code snippets

    np_token-act-pair-logits · gpt-4o-mini

    code and networking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Waray
    -0.51
     labi
    -0.44
     Pierson
    -0.44
     Carthag
    -0.44
    Autoritní
    -0.43
     Agrico
    -0.42
    ρακ
    -0.42
    vacy
    -0.42
     Pik
    -0.42
     goto
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.75
    ublic
    0.65
    enumi
    0.63
     betweenstory
    0.60
    hs
    0.60
    $_['
    0.60
    modelBuilder
    0.59
    hon
    0.59
    RectangleBorder
    0.58
    adaptiveStyles
    0.57
    Act Density 1.159%

    No Known Activations