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

    Neuronpedia

    INDEX
    Explanations

    assignment and declaration operators in code

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

    code blocks or structural elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.98
     $_"
    -0.82
     $_(
    -0.79
     Reſ
    -0.79
     Houſe
    -0.76
     ſche
    -0.75
     Autorizaciones
    -0.75
     houſe
    -0.75
     myſelf
    -0.74
     ſta
    -0.72
    POSITIVE LOGITS
    BorderFactory
    0.36
    Autoritní
    0.35
     autorytatywna
    0.32
     خارجية
    0.26
    complexContent
    0.24
     h
    0.24
    RenderAtEndOf
    0.24
     a
    0.24
     papan
    0.23
     Verfassung
    0.23
    Act Density 0.001%

    No Known Activations