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

    Neuronpedia

    INDEX
    Explanations

    refugees and displaced people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discorso
    0.57
    ancia
    0.57
    úsica
    0.53
    ar
    0.52
     diarias
    0.52
     sól
    0.51
    ura
    0.50
    arita
    0.50
     biblical
    0.49
    arach
    0.49
    POSITIVE LOGITS
    s
    0.69
    R
    0.64
    ని
    0.62
    パ
    0.61
    C
    0.61
     ornaments
    0.60
    premier
    0.59
    пи
    0.59
    P
    0.57
     condiments
    0.57
    Act Density 0.000%

    No Known Activations