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

    Neuronpedia

    INDEX
    Explanations

    code structure and data manipulation terms

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

    programming iteration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.52
     noDo
    -0.51
    tonode
    -0.50
     незавершена
    -0.48
     informée
    -0.47
     مشين
    -0.47
    DoubleQuotes
    -0.47
    astify
    -0.46
    ьажоргаш
    -0.44
     <>",
    -0.44
    POSITIVE LOGITS
    OCCURRED
    0.47
    éia
    0.46
     cycles
    0.45
    cycles
    0.41
    脚注の使い方
    0.40
     Programming
    0.40
    省市镇
    0.39
    itoare
    0.39
     uș
    0.39
    pă
    0.39
    Act Density 0.005%

    No Known Activations