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

    Neuronpedia

    INDEX
    Explanations

    colors and wavelengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    பி
    0.44
     текст
    0.43
    ବା
    0.43
     चाहते
    0.43
     засто
    0.42
     EXAMINATION
    0.41
    膠
    0.41
     攵
    0.41
     يكن
    0.41
     применения
    0.40
    POSITIVE LOGITS
    learner
    0.50
     expectativas
    0.48
    erson
    0.45
    light
    0.45
    hew
    0.44
    delivered
    0.44
    Laura
    0.43
    ward
    0.42
    expectation
    0.42
    wór
    0.42
    Act Density 0.001%

    No Known Activations