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

    Neuronpedia

    INDEX
    Explanations

    references to sharks in various contexts

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

    swimming and diving

    np_acts-logits-general · gemini-2.0-flash

    scuba diving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    didSet
    -0.71
    SequentialGroup
    -0.64
     ferrovia
    -0.62
    __":
    -0.60
    MLLoader
    -0.57
     hamsters
    -0.57
     getItemId
    -0.57
     MainAxisSize
    -0.55
    NameInMap
    -0.54
    naphthal
    -0.53
    POSITIVE LOGITS
     dive
    1.22
     diving
    1.03
     Dive
    0.99
     scuba
    0.94
     dives
    0.93
     divers
    0.92
    Dive
    0.92
     diver
    0.91
     Diving
    0.88
    dive
    0.88
    Act Density 0.128%

    No Known Activations