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

    Neuronpedia

    INDEX
    Explanations

    geographical names and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.84
    es
    0.54
    er
    0.54
    ,
    0.52
    os
    0.50
    oretically
    0.50
     of
    0.50
    en
    0.49
     to
    0.48
    ي
    0.47
    POSITIVE LOGITS
    Depois
    0.66
    ക്കുറിച്ച്
    0.63
    ên
    0.62
    Three
    0.60
    ૦
    0.60
    ńskiej
    0.60
    Communications
    0.58
    Nome
    0.58
    <unused377>
    0.57
    Κ
    0.57
    Act Density 0.616%

    No Known Activations