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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mess
    -0.07
     hton
    -0.07
    owego
    -0.07
    Mus
    -0.07
    runs
    -0.07
    baseUrl
    -0.07
    Bus
    -0.06
    Matt
    -0.06
     moins
    -0.06
    Ž
    -0.06
    POSITIVE LOGITS
     translated
    0.07
     researcher
    0.07
    -known
    0.07
    召回
    0.07
     sank
    0.07
     spheres
    0.07
     disappears
    0.07
    _left
    0.07
    𫓯
    0.07
     lecturer
    0.07
    Act Density 0.010%

    No Known Activations