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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    írez
    0.43
     Dons
    0.42
     profesores
    0.41
     pernicious
    0.41
    niew
    0.40
     atributo
    0.40
     invis
    0.39
     diez
    0.39
     ට
    0.39
    ="
    0.39
    POSITIVE LOGITS
     flattening
    0.53
    েন্টের
    0.46
    儩
    0.46
    ありません
    0.45
    डले
    0.45
    ೇವಿನ
    0.44
    BQ
    0.44
    いが
    0.44
    োক
    0.43
    Ⅼ
    0.43
    Act Density 0.003%

    No Known Activations