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

    Neuronpedia

    INDEX
    Explanations

    characters with accent marks in words

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

    í accented characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.70
     AssemblyVersion
    -0.69
    majánló
    -0.60
     nabíz
    -0.60
     AssemblyCompany
    -0.59
     země
    -0.59
     hjemmes
    -0.58
    AutoresizingMask
    -0.57
     debía
    -0.56
     navíc
    -0.56
    POSITIVE LOGITS
    í
    2.05
    Í
    1.41
    iacute
    0.98
     Í
    0.94
     í
    0.90
    rí
    0.85
    lí
    0.81
    íí
    0.77
    hí
    0.75
    dí
    0.73
    Act Density 0.003%

    No Known Activations