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

    Neuronpedia

    INDEX
    Explanations

    high-value numerical indicators or parameters in mathematical expressions

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

    proof or solution sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يكب
    -0.62
    ⟬
    -0.62
    typeorm
    -0.60
    principalColumn
    -0.60
     ſind
    -0.60
    iſchen
    -0.60
    ffindor
    -0.60
    tonsoft
    -0.59
    ValueStyle
    -0.59
    actylus
    -0.58
    POSITIVE LOGITS
    ↵↵
    0.45
     publicités
    0.34
     odkazy
    0.34
     (
    0.33
     Fuchs
    0.33
     Fournier
    0.33
    <eos>
    0.32
    Bronnen
    0.31
    <strong>
    0.31
     information
    0.30
    Act Density 0.011%

    No Known Activations