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

    Neuronpedia

    INDEX
    Explanations

    references to clinical studies, therapies, and patient-related data in a medical context

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

    Bullet points

    np_acts-logits-general · gemini-2.0-flash

    bullet points and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thats
    -0.99
     didnt
    -0.97
     wasnt
    -0.93
     doesnt
    -0.93
     youll
    -0.91
     couldnt
    -0.90
     isnt
    -0.86
     thats
    -0.86
     youre
    -0.85
     theyre
    -0.84
    POSITIVE LOGITS
     •
    2.01
    •
    1.77
    )•
    1.47
    .•
    1.33
    •.
    1.09
     ••
    0.97
     ·
    0.95
    ,”
    0.89
    •••
    0.89
    ⚫
    0.88
    Act Density 0.182%

    No Known Activations