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

    Neuronpedia

    INDEX
    Explanations

    expressions related to belief and perception

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

    followed by "to," "as," or "of"

    np_acts-logits-general · gemini-2.0-flash

    suggest or state something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SqlParameter
    -0.55
     seen
    -0.50
     تضيفلها
    -0.48
     actionPerformed
    -0.47
    ifest
    -0.45
    astify
    -0.44
    觉得
    -0.43
    seem
    -0.43
    thema
    -0.43
    անդ
    -0.43
    POSITIVE LOGITS
     is
    0.87
     could
    0.84
     has
    0.82
     abbia
    0.82
     will
    0.80
     had
    0.79
     exists
    0.77
     might
    0.77
     would
    0.76
     existed
    0.74
    Act Density 0.384%

    No Known Activations