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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to health, ethics, and spirituality

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

    Follows "is," "are," "as," or "a."

    np_acts-logits-general · gemini-2.0-flash

    defining a term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.69
     vulgaires
    -0.67
    SharedCtor
    -0.66
     nakalista
    -0.63
     theirs
    -0.63
    ğraf
    -0.62
     obstante
    -0.59
    Попис
    -0.59
    равда
    -0.58
     MainAxisSize
    -0.58
    POSITIVE LOGITS
     refers
    0.82
     inaczej
    0.76
     basically
    0.72
     term
    0.71
     fancy
    0.71
    basically
    0.67
     aquellas
    0.66
     collection
    0.65
     any
    0.64
     aquel
    0.64
    Act Density 0.677%

    No Known Activations