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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the backslash character in various contexts

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

    underlined mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.90
     propOrder
    -0.86
    RegressionTest
    -0.81
    principalColumn
    -0.79
    transQ
    -0.78
     MainAxisSize
    -0.74
    StructEnd
    -0.73
    -0.71
    ⓧ
    -0.68
    TintMode
    -0.65
    POSITIVE LOGITS
     text
    0.44
    :].
    0.44
     video
    0.41
     script
    0.40
    The
    0.40
     clip
    0.40
     balloon
    0.39
    orded
    0.39
     translucent
    0.39
    begin
    0.38
    Act Density 0.002%

    No Known Activations