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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to biological mechanisms

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

    preceding "mechanism," "function," or "layer."

    np_acts-logits-general · gemini-2.0-flash

    mechanism underlying or behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.80
     مرئيه
    -0.78
    enumii
    -0.77
    enumi
    -0.75
    )|^{
    -0.71
    ValueStyle
    -0.62
    -0.62
    TagMode
    -0.60
     snippetHide
    -0.60
     <<<<<<<<<<<<<<
    -0.59
    POSITIVE LOGITS
    (
    2.81
    (-
    1.24
    (_
    1.06
    (
    1.05
    [
    1.03
    (\
    1.00
    ($
    0.98
    (+
    0.98
    ("
    0.97
    ((
    0.96
    Act Density 0.730%

    No Known Activations