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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms related to continuity and differentiability in functions

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

    Mathematical notation related to derivatives

    np_acts-logits-general · gemini-2.0-flash

    at points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RunAsync
    -0.65
    PerformLayout
    -0.62
     Anſ
    -0.61
    parsedMessage
    -0.60
    ynchronously
    -0.57
     Савезне
    -0.57
     InputDecoration
    -0.57
     Affiliations
    -0.56
    "]();
    -0.56
     fasci
    -0.56
    POSITIVE LOGITS
     at
    1.40
     near
    1.30
     tại
    1.19
     somewhere
    1.09
    near
    1.06
     anywhere
    1.05
    Near
    1.04
     Near
    0.96
    somewhere
    0.95
     ở
    0.87
    Act Density 0.820%

    No Known Activations