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

    Neuronpedia

    INDEX
    Explanations

    dust motes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kombin
    0.49
    섞
    0.43
    ަތ
    0.42
    cuterie
    0.42
    ก็จะ
    0.42
    atzeko
    0.40
    zości
    0.40
    Ꮝ
    0.40
     vall
    0.38
     konkur
    0.38
    POSITIVE LOGITS
     January
    0.44
     वर्ष
    0.43
     marchio
    0.40
     gennaio
    0.40
     இடையே
    0.40
     waarin
    0.39
     {{\
    0.39
     during
    0.39
     duy
    0.38
     янва
    0.38
    Act Density 0.005%

    No Known Activations