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

    Neuronpedia

    INDEX
    Explanations

    references to unique identifiers and memory allocation in programming contexts

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

    my label={ }

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Königin
    -0.35
     a
    -0.35
     zijne
    -0.34
     récemment
    -0.32
     Bevölkerung
    -0.31
     their
    -0.31
     jūs
    -0.30
     políticas
    -0.30
     the
    -0.29
     dezelve
    -0.29
    POSITIVE LOGITS
    EDEFAULT
    0.93
    دانشنامهٔ
    0.91
    transQ
    0.89
     للاسماء
    0.89
     tartalomajánló
    0.85
    0.85
    0.84
     виправивши
    0.84
    InjectAttribute
    0.84
     ujednoznacz
    0.84
    Act Density 0.078%

    No Known Activations