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

    Neuronpedia

    INDEX
    Explanations

    references to positions, titles, and organizational roles

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

    'th term of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LLocation
    -0.68
    󠁴
    -0.66
     ſeine
    -0.65
    AddTagHelper
    -0.64
     Italijanski
    -0.63
    hoeddwyd
    -0.62
    inSlope
    -0.62
     Geſch
    -0.61
    makeConstraints
    -0.61
     iconFacebook
    -0.61
    POSITIVE LOGITS
    err
    0.34
    vo
    0.33
    auto
    0.31
    во
    0.31
     destroyed
    0.31
     err
    0.31
     in
    0.31
     hell
    0.30
     for
    0.30
    imageUrl
    0.29
    Act Density 0.828%

    No Known Activations