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

    Neuronpedia

    INDEX
    Explanations

    structural elements and references in technical or scientific documents

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

    Text surrounding figure references

    np_acts-logits-general · gemini-2.0-flash

    specific technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
    ↵↵
    -0.47
     
    -0.44
    hawar
    -0.42
    ?
    -0.42
     I
    -0.41
     “
    -0.41
     ·
    -0.40
    <em>
    -0.40
     "
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    0.89
    Бахар
    0.88
    featureID
    0.84
    脚注の使い方
    0.83
    WireFormatLite
    0.82
    oa̍t
    0.81
    Geplaatst
    0.79
     tartalomajánló
    0.77
     незавершена
    0.76
     <=",
    0.75
    Act Density 1.276%

    No Known Activations