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

    Neuronpedia

    INDEX
    Explanations

    references to marine animals and specific behavioral interactions involving them

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

    sharks and whales

    np_acts-logits-general · gemini-2.0-flash

    whales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.73
     pheasant
    -0.64
    SourceChecksum
    -0.61
     insects
    -0.61
    asants
    -0.58
     crickets
    -0.57
     Insects
    -0.57
     squirrels
    -0.55
     sparrows
    -0.55
     Bosco
    -0.55
    POSITIVE LOGITS
     whale
    0.97
     whales
    0.91
    Whale
    0.82
    whale
    0.82
     Whale
    0.79
     Whales
    0.72
    鯨
    0.68
    鲸
    0.67
     seal
    0.66
     bale
    0.65
    Act Density 0.117%

    No Known Activations