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

    Neuronpedia

    INDEX
    Explanations

    Elon Musk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tesla
    0.62
    Tesla
    0.56
    tesla
    0.51
     tesla
    0.51
     Terrorism
    0.48
     Tes
    0.45
     Tena
    0.44
     TensorFlow
    0.43
     Tennyson
    0.42
     tess
    0.41
    POSITIVE LOGITS
    Jeff
    0.61
     Jeff
    0.59
     musk
    0.56
     Musk
    0.55
    麝
    0.46
    マスク
    0.46
     mask
    0.45
     Mask
    0.44
     Ree
    0.44
    Elon
    0.43
    Act Density 0.004%

    No Known Activations