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

    Neuronpedia

    INDEX
    Explanations

    columns, elements, fluctuations, extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saga
    0.81
     Dewan
    0.80
    EDY
    0.79
     विधाय
    0.78
    ekra
    0.75
    bildungs
    0.75
     kantor
    0.74
    \|$.
    0.74
    nesia
    0.73
    fixture
    0.73
    POSITIVE LOGITS
     shouldn
    0.83
    е
    0.79
     blij
    0.77
    다
    0.74
     weren
    0.74
    Okay
    0.72
    п
    0.72
     okay
    0.71
    啊
    0.69
    ц
    0.68
    Act Density 0.002%

    No Known Activations