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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or titles related to events or entities in a structured context

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

    Wikipedia and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.59
    tagHelperRunner
    -0.57
     kasarigan
    -0.56
    jsonwebtoken
    -0.55
     незавершена
    -0.53
    الإنجليزية
    -0.52
    DebuggerStep
    -0.52
     otomatig
    -0.52
    Попис
    -0.51
     Taktlose
    -0.50
    POSITIVE LOGITS
    sepeda
    0.35
     polémica
    0.35
     Wikipedia
    0.34
     autorytatywna
    0.34
     écrans
    0.32
     Syrie
    0.31
    depuis
    0.31
    ём
    0.30
    ficamente
    0.30
    fatter
    0.30
    Act Density 0.273%

    No Known Activations