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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that indicate analysis and comparison within various contexts

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

    definition or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.60
    ⓧ
    -0.59
    iſter
    -0.57
    verwijspagina
    -0.56
    Diwedd
    -0.54
    StructEnd
    -0.54
    dersfield
    -0.54
     betweenstory
    -0.53
    AddTagHelper
    -0.53
    iſten
    -0.52
    POSITIVE LOGITS
     is
    1.42
     ialah
    1.25
     adalah
    1.22
    的是
    1.16
    คือ
    1.06
     consists
    0.93
     заключается
    0.90
     involves
    0.90
    的就是
    0.89
     consiste
    0.88
    Act Density 0.380%

    No Known Activations