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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters

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

    German words with long s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `
    -0.25
    addGap
    -0.23
     "__
    -0.22
    Vegeu
    -0.22
     LCCN
    -0.22
    [_
    -0.21
    stdlib
    -0.21
     وصلة
    -0.21
    [`
    -0.20
     suger
    -0.20
    POSITIVE LOGITS
    iſche
    0.94
     ſeines
    0.93
     erſt
    0.93
     erſten
    0.92
     ſeinem
    0.92
     ſehr
    0.91
    ſelben
    0.91
     ſchon
    0.91
    ðsíða
    0.91
    iſchen
    0.89
    Act Density 1.026%

    No Known Activations