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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

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

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.78
     HttpNotFound
    -0.71
     kasarigan
    -0.65
     Biôgrafia
    -0.65
    ↻
    -0.64
    twimg
    -0.64
    StructEnd
    -0.63
    transQ
    -0.61
    oinette
    -0.61
    fromnode
    -0.60
    POSITIVE LOGITS
     etc
    0.40
     among
    0.40
    among
    0.35
     그리고
    0.35
    ktı
    0.34
     sauvages
    0.34
     Dijo
    0.34
    gaande
    0.33
     daarvan
    0.33
    osť
    0.32
    Act Density 0.047%

    No Known Activations