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

    Neuronpedia

    INDEX
    Explanations

    specific programming terms and their associated features

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

    technical terms and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.34
    цездатний
    -0.34
     desmotiv
    -0.33
    untos
    -0.33
    vast
    -0.33
    midt
    -0.32
    tokenizer
    -0.31
     cuchara
    -0.31
     slow
    -0.30
     składa
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
     '\\;'
    0.65
     dAtA
    0.60
     Biôgrafia
    0.59
    الحياه
    0.58
     queſta
    0.58
    0.58
     uLocal
    0.57
    HandlerContext
    0.56
     صوتيه
    0.56
    Act Density 0.193%

    No Known Activations