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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in programming code

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
    Gemeinden
    -0.43
     Reim
    -0.41
     Ivanov
    -0.40
    parentElement
    -0.39
    Française
    -0.39
     volontà
    -0.38
     Monteiro
    -0.37
     Lop
    -0.37
     MTA
    -0.36
    POSITIVE LOGITS
    1.00
    StructEnd
    0.59
    0.59
    ₂+
    0.58
    0.58
    0.54
     Personne
    0.54
    0.54
    Autoritní
    0.53
     indisponible
    0.53
    Act Density 0.031%

    No Known Activations