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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and programming-related concepts such as coordinates, paths, and variables

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

    programming context definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    retudo
    -0.36
     متعلقه
    -0.33
    óval
    -0.32
     producenta
    -0.31
     szczegół
    -0.30
     spô
    -0.30
     telefónica
    -0.29
    simult
    -0.29
     houſe
    -0.29
     cauſe
    -0.29
    POSITIVE LOGITS
     converted
    0.77
    uxxxx
    0.68
     transformed
    0.64
    CopyWith
    0.64
    parsedMessage
    0.61
     without
    0.60
    converted
    0.60
     виправивши
    0.59
     nakalista
    0.59
     convertible
    0.58
    Act Density 0.069%

    No Known Activations