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

    Neuronpedia

    INDEX
    Explanations

    references to hands-on experience or activities

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

    hands-on and hands-free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.53
    她們
    -0.44
     quota
    -0.43
     InputDecoration
    -0.43
     quotas
    -0.43
     تكبرها
    -0.42
    ▣
    -0.41
     snipers
    -0.40
     createStore
    -0.40
     Administrativna
    -0.40
    POSITIVE LOGITS
    Hands
    1.26
     Hands
    1.23
     hands
    1.16
    hands
    1.15
     HANDS
    1.14
     Hände
    0.75
     manos
    0.75
     mãos
    0.62
     tangan
    0.60
     handen
    0.54
    Act Density 0.002%

    No Known Activations