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

    Neuronpedia

    INDEX
    Explanations

    the presence of quotes or dialogue

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

    Nicknames or quoted names

    np_acts-logits-general · gemini-2.0-flash

    quoted nicknames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.64
     Aleksandra
    -0.60
     purpoſe
    -0.59
     Katharine
    -0.58
     fubject
    -0.58
     personeel
    -0.56
     Amalia
    -0.56
     Mahabhar
    -0.55
     Majefty
    -0.55
     avoient
    -0.55
    POSITIVE LOGITS
     Doc
    0.75
    GEBURTSDATUM
    0.73
     Bob
    0.72
    uzzy
    0.72
     Big
    0.68
    ResumeLayout
    0.68
     Pete
    0.66
     Smit
    0.65
    RegistryLite
    0.64
     Charlie
    0.64
    Act Density 0.194%

    No Known Activations