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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement in textual structures

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

    data structures and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lower
    -0.41
     baixar
    -0.36
     تص
    -0.36
     שוליים
    -0.35
     navíc
    -0.35
     guías
    -0.35
     stabilize
    -0.35
    पया
    -0.35
     obsah
    -0.34
     upra
    -0.34
    POSITIVE LOGITS
    TextHelper
    0.54
    ########.
    0.54
     snippetHide
    0.52
    HostException
    0.52
     noDo
    0.52
     الرياضيه
    0.50
    JsonHelper
    0.49
     newOwner
    0.49
    querque
    0.49
    herme
    0.49
    Act Density 0.123%

    No Known Activations