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

    Neuronpedia

    INDEX
    Explanations

    keywords related to healthcare innovation and operational improvements

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

    preceding prepositions

    np_acts-logits-general · gemini-2.0-flash

    organizational concepts and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sometimes
    -0.66
     Sometimes
    -0.59
     иногда
    -0.55
     oder
    -0.55
     vaguely
    -0.54
    Sometimes
    -0.54
    !)
    -0.54
     maybe
    -0.53
    (?)
    -0.53
     occasionally
    -0.52
    POSITIVE LOGITS
     across
    0.92
     itſelf
    0.85
    across
    0.84
     throughout
    0.83
     conformément
    0.81
    throughout
    0.81
     themſelves
    0.81
     attraverso
    0.80
     both
    0.78
     poprzez
    0.77
    Act Density 0.459%

    No Known Activations