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

    Neuronpedia

    INDEX
    Explanations

    references to notable authors, filmmakers, and iconic characters from popular media

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

    names and titles of works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rubber
    -0.49
    rubber
    -0.43
     Rubber
    -0.42
    etton
    -0.41
     tennis
    -0.41
    PDOException
    -0.40
     forwarding
    -0.40
    Rubber
    -0.39
     shark
    -0.39
     Stadium
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.66
    ampunk
    0.62
     historische
    0.60
     ModelExpression
    0.58
    Bibliograf
    0.56
     يتيمه
    0.54
    AndEndTag
    0.53
    __::
    0.53
     nonUne
    0.50
     itſelf
    0.49
    Act Density 0.025%

    No Known Activations