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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming-related content

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

    Code or email addresses followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -0.78
    Personensuche
    -0.75
    Hochspringen
    -0.75
    fjspx
    -0.73
    StoryboardSegue
    -0.70
     Anſ
    -0.69
     poffible
    -0.67
     himſelf
    -0.66
    ScopeManager
    -0.66
     myſelf
    -0.66
    POSITIVE LOGITS
     message
    0.62
    message
    0.54
     messaggio
    0.48
     Message
    0.47
    <<"
    0.47
     dicendo
    0.46
     msg
    0.46
     mensagem
    0.45
    illem
    0.45
    msg
    0.44
    Act Density 0.058%

    No Known Activations