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

    Neuronpedia

    INDEX
    Explanations

    time and frequency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     από
    0.84
    Translation
    0.84
    uddersfield
    0.83
     अली
    0.81
     మరియు
    0.81
     και
    0.80
     置
    0.76
    testAvg
    0.75
     पुश
    0.74
     Translation
    0.74
    POSITIVE LOGITS
    pipes
    0.85
    neurons
    0.82
    nuts
    0.82
    b
    0.78
    w
    0.78
     conform
    0.76
    polls
    0.75
    screens
    0.75
    squares
    0.74
     hips
    0.73
    Act Density 0.000%

    No Known Activations