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

    Neuronpedia

    INDEX
    Explanations

    end punctuation or sentence delimiters

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

    java util classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.63
    -------------</
    -0.56
     <<<<<<<<<<<<<<
    -0.52
    setVerticalGroup
    -0.52
    GEBURTS
    -0.52
     ModelExpression
    -0.49
     queſta
    -0.48
    WithIOException
    -0.48
    FieldOffsetTable
    -0.48
    providedIn
    -0.48
    POSITIVE LOGITS
     informée
    0.39
     friends
    0.38
     Cole
    0.37
     cole
    0.37
     median
    0.37
     grandparents
    0.36
    PATTERN
    0.36
    kolle
    0.36
    median
    0.36
     pattern
    0.35
    Act Density 0.001%

    No Known Activations