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

    Neuronpedia

    INDEX
    Explanations

    special characters and accented letters in text

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

    accented vowels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     télévis
    -0.54
     يتيمه
    -0.52
    afficheront
    -0.52
     trône
    -0.51
     Encuentra
    -0.49
     Gestión
    -0.48
    存于互联网档案馆
    -0.47
     Construcción
    -0.47
     oír
    -0.46
     réaliste
    -0.45
    POSITIVE LOGITS
    ó
    1.13
    Ó
    0.94
     ó
    0.83
     Ó
    0.78
    oacute
    0.74
     pó
    0.65
     bó
    0.62
    ók
    0.59
    ró
    0.56
    Oacute
    0.56
    Act Density 0.022%

    No Known Activations