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

    Neuronpedia

    INDEX
    Explanations

    numerical values and coordinates typically used in graphical or mapping contexts

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

    <start_of_turn>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LayoutStyle
    -0.42
     understandable
    -0.30
    ziehen
    -0.29
     sauvage
    -0.28
     derin
    -0.28
     braccio
    -0.28
     oreja
    -0.27
     hombro
    -0.27
    rosas
    -0.27
    */),
    -0.27
    POSITIVE LOGITS
     שוליים
    0.79
     utafitiHapana
    0.67
     autorytatywna
    0.64
    はじめに
    0.64
    Хьажоргаш
    0.64
     saites
    0.61
    Diwedd
    0.59
    Cyfarwyddwr
    0.59
    Зноскі
    0.58
    InjectAttribute
    0.57
    Act Density 0.001%

    No Known Activations