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

    Neuronpedia

    INDEX
    Explanations

    noise level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pancreatic
    0.41
    ayscale
    0.39
     سعد
    0.37
     Saad
    0.37
     cyn
    0.36
     fiducia
    0.36
    结算
    0.36
     melancholy
    0.35
     cynical
    0.35
     hydrated
    0.35
    POSITIVE LOGITS
     noise
    1.80
    Noise
    1.64
     Noise
    1.61
    noise
    1.55
    噪音
    1.44
    噪声
    1.40
     noisy
    1.34
     ruido
    1.25
     шум
    1.13
     nois
    1.12
    Act Density 0.013%

    No Known Activations