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

    Neuronpedia

    INDEX
    Explanations

    direct quotations or speech markers in the text

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

    explaining what will happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.76
     Италијани
    -0.69
    ſicht
    -0.67
    NUMX
    -0.64
     beſch
    -0.62
     مرئيه
    -0.62
     zwiſchen
    -0.62
     snippetHide
    -0.62
     autorytatywna
    -0.62
     محفوظة
    -0.61
    POSITIVE LOGITS
    TagMode
    0.40
    tagHelperRunner
    0.39
    setVerticalGroup
    0.31
     ComVisible
    0.31
     yhte
    0.31
     Ponce
    0.30
     fourrure
    0.30
     faptul
    0.29
     trous
    0.28
     dumne
    0.28
    Act Density 0.021%

    No Known Activations