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

    Neuronpedia

    INDEX
    Explanations

    phrases related to shared characteristics or commonalities among groups or entities

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

    common aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.55
    MLLoader
    -0.53
    utnik
    -0.47
    Organisateur
    -0.47
    CloseOperation
    -0.47
    __":
    -0.47
     volna
    -0.47
    ValueStyle
    -0.47
    Gambas
    -0.46
    already
    -0.46
    POSITIVE LOGITS
    共通
    1.41
     common
    1.30
    common
    1.07
     gemens
    0.99
     COMMON
    0.98
     común
    0.96
     comum
    0.93
    Common
    0.92
     ortak
    0.91
     Common
    0.90
    Act Density 0.114%

    No Known Activations