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

    Neuronpedia

    INDEX
    Explanations

    references to fingers and hands, particularly focusing on their positions and interactions

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

    body extremities with left/right modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.57
    GEBURTSDATUM
    -0.56
     ModelExpression
    -0.48
     propOrder
    -0.46
     récolte
    -0.44
    Personendaten
    -0.42
    parsedMessage
    -0.40
    Життєпис
    -0.39
     antaranya
    -0.39
     Lingkungan
    -0.39
    POSITIVE LOGITS
     arms
    0.63
     fingers
    0.62
     finger
    0.59
     hands
    0.57
     arm
    0.56
     hand
    0.56
     Hand
    0.54
     Finger
    0.52
     fingertips
    0.52
     feet
    0.51
    Act Density 0.078%

    No Known Activations