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

    Neuronpedia

    INDEX
    Explanations

    questions and direct addresses to the user

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

    conversational phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clues
    -0.36
     wyda
    -0.36
     rags
    -0.36
     drept
    -0.35
     constater
    -0.35
     likelihood
    -0.35
     proven
    -0.35
     evidence
    -0.34
    coats
    -0.34
     nhãn
    -0.34
    POSITIVE LOGITS
     للاسماء
    0.65
    GEBURTSDATUM
    0.61
     surla
    0.57
    ſelf
    0.55
     kaarangay
    0.53
     Normdatei
    0.53
    المكان
    0.52
    ſelves
    0.52
    CopyWith
    0.50
     MonoBehaviour
    0.50
    Act Density 0.025%

    No Known Activations