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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating suitability or options for a specific purpose

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

    choice for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     run
    -0.35
     selling
    -0.33
     Bru
    -0.32
    컨
    -0.31
    toHaveBeenCalled
    -0.30
     ran
    -0.30
    امي
    -0.30
     momen
    -0.30
     sales
    -0.30
     verkoop
    -0.29
    POSITIVE LOGITS
    IntoConstraints
    0.91
    0.68
    httphttps
    0.68
     GenerationType
    0.67
    DockStyle
    0.67
     للاسماء
    0.61
     InputDecoration
    0.60
     Normdatei
    0.60
    KURZBESCHREIBUNG
    0.60
     autorytatywna
    0.58
    Act Density 0.035%

    No Known Activations