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

    Neuronpedia

    INDEX
    Explanations

    break down what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marche
    0.45
    èvre
    0.43
    }%
    0.41
     berfungsi
    0.41
     rumah
    0.41
     экологи
    0.40
     expresión
    0.39
     रसोई
    0.39
     organizada
    0.39
     rhiz
    0.38
    POSITIVE LOGITS
    arbit
    0.43
    Arbit
    0.42
    asius
    0.39
    epen
    0.38
    icut
    0.37
    दु
    0.37
    numer
    0.37
    ())))
    0.37
    ocaust
    0.37
    ᔭ
    0.37
    Act Density 0.000%

    No Known Activations