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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and greetings

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

    Salut and honey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EditorGUILayout
    -0.34
    การ
    -0.33
    脚注の使い方
    -0.31
     
    -0.31
     הר
    -0.31
     cite
    -0.30
     location
    -0.30
    ỗ
    -0.30
     COVID
    -0.30
     fa
    -0.29
    POSITIVE LOGITS
    GEBURTSDATUM
    0.68
    ंदीखरीदारी
    0.66
    MemoryWarning
    0.65
     فريبيس
    0.62
     Girlfriend
    0.61
    girlfriend
    0.60
     Италијани
    0.59
    󠁴
    0.59
    haviour
    0.59
     désolés
    0.59
    Act Density 0.103%

    No Known Activations