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

    Neuronpedia

    INDEX
    Explanations

    the presence of syntactic structures typical in programming or code

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

    insert, insertBefore, arithmetic operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.42
     @"/
    -0.41
     clu
    -0.37
    ()<
    -0.37
    arXiv
    -0.37
    ]<<
    -0.36
     ◆
    -0.36
    keyColumn
    -0.35
     /><
    -0.35
    bilt
    -0.34
    POSITIVE LOGITS
     Hongrie
    0.66
     plufieurs
    0.64
     Geſ
    0.59
    parsedMessage
    0.57
     auroit
    0.56
    majánló
    0.56
     Verſ
    0.56
     feroit
    0.56
    pingente
    0.56
     pouvoit
    0.54
    Act Density 0.458%

    No Known Activations