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

    Neuronpedia

    INDEX
    Explanations

    occurrences of copyright-related information or attributions

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

    file paths and programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.82
    Personendaten
    -0.82
     المعيارى
    -0.70
     BoxFit
    -0.69
     betweenstory
    -0.69
    ſſung
    -0.66
     nakalista
    -0.66
    Tikang
    -0.65
    TagMode
    -0.65
     pinulongan
    -0.64
    POSITIVE LOGITS
     fusca
    0.32
     Architecture
    0.32
     Company
    0.32
    following
    0.30
     Project
    0.30
     Following
    0.29
     refreshToken
    0.28
     Paper
    0.28
     Ball
    0.27
    ../../
    0.27
    Act Density 0.001%

    No Known Activations