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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sunlight
    -0.06
    Her
    -0.06
    ategic
    -0.06
    Taylor
    -0.06
     Ri
    -0.06
     بأ
    -0.06
     który
    -0.06
     psychedelic
    -0.06
    .RestController
    -0.06
     accumulate
    -0.06
    POSITIVE LOGITS
    _MIDDLE
    0.07
    |M
    0.07
     scorer
    0.06
    劃
    0.06
     USSR
    0.06
    .nih
    0.06
     kromě
    0.06
     lumber
    0.06
    وز
    0.06
    stay
    0.06
    Act Density 0.000%

    No Known Activations