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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical notations

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

    mathematical expressions with fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.97
    majánló
    -0.97
     ſch
    -0.96
     ſta
    -0.95
    ſelves
    -0.94
     ſche
    -0.92
     raiſ
    -0.91
     ſtand
    -0.91
     faſt
    -0.90
     queſta
    -0.88
    POSITIVE LOGITS
    {
    0.65
    _{
    0.60
    frac
    0.50
    dfrac
    0.50
     
    0.48
    <sub>
    0.46
    <
    0.46
    }_{
    0.46
     {
    0.44
    (
    0.43
    Act Density 0.051%

    No Known Activations