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

    Neuronpedia

    INDEX
    Explanations

    specific numerical identifiers or references in a document

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

    numbered list item nine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.56
     فريبيس
    -0.51
    WriteTagHelper
    -0.45
    guantes
    -0.45
    觎
    -0.42
    ziasztok
    -0.42
    Aub
    -0.42
    actionMode
    -0.42
     actionMode
    -0.41
    arakat
    -0.40
    POSITIVE LOGITS
     Nine
    0.51
     NINE
    0.49
    十
    0.48
    Nine
    0.48
     Tenth
    0.44
     Ninth
    0.44
     Wikimedijinoj
    0.44
     nine
    0.44
     tenth
    0.43
    tenth
    0.43
    Act Density 0.053%

    No Known Activations