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

    Neuronpedia

    INDEX
    Explanations

    references to violence in animated contexts

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

    characters, characters, capable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.59
     ligiloj
    -0.57
     препратки
    -0.49
    tagHelperRunner
    -0.47
     liitty
    -0.45
    awtextra
    -0.43
    XmlAccessType
    -0.41
    WriteTagHelper
    -0.41
    MENAFN
    -0.40
    createNewFile
    -0.40
    POSITIVE LOGITS
    ViewFeatures
    0.46
    addGap
    0.42
    gsSP
    0.37
     lume
    0.37
     characters
    0.36
     Characters
    0.36
    0.36
    0.36
     implied
    0.34
     Cad
    0.33
    Act Density 0.082%

    No Known Activations