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

    Neuronpedia

    INDEX
    Explanations

    references to specific persons or entities in a narrative context

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

    symbols and uncommon words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.65
    -0.54
    *~*~
    -0.53
    AnimationsModule
    -0.52
    MemoryWarning
    -0.52
    Rujuakan
    -0.49
     queſta
    -0.49
    writeField
    -0.48
     laſſen
    -0.47
    postsleuth
    -0.47
    POSITIVE LOGITS
     nakalista
    0.50
    Espèce
    0.48
    awtextra
    0.44
     Chwiliwch
    0.40
    पया
    0.39
    AndEndTag
    0.37
     désolés
    0.34
     CreateTagHelper
    0.32
     autorytatywna
    0.32
     lenker
    0.32
    Act Density 0.001%

    No Known Activations