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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    Text following "Let" or "Suppose"

    np_acts-logits-general · gemini-2.0-flash

    finding mathematical equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <code>
    -0.59
    ⇑
    -0.59
     
    -0.59
    <em>
    -0.55
     $\
    -0.55
    SequentialGroup
    -0.54
    <sup>
    -0.54
    ..\..\
    -0.53
    <strong>
    -0.53
    iritto
    -0.52
    POSITIVE LOGITS
     ſal
    0.76
     '\\;'
    0.72
     eſt
    0.67
    +#+#
    0.66
     uſ
    0.65
     ſp
    0.65
     typelib
    0.64
     ſu
    0.63
     ++)
    0.62
     uſe
    0.62
    Act Density 1.579%

    No Known Activations