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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure elements

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    legal notifications and political party names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infine
    -0.65
     again
    -0.60
     another
    -0.60
    <eos>
    -0.59
     I
    -0.58
     other
    -0.55
     he
    -0.54
     we
    -0.53
    .
    -0.52
     lastly
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.99
    TagMode
    0.97
     Efq
    0.92
     Administrativna
    0.85
    tagHelperRunner
    0.84
    setVerticalGroup
    0.82
     ostavi
    0.82
    IsContent
    0.81
    bewerken
    0.80
    ſelf
    0.80
    Act Density 0.243%

    No Known Activations