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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    volent
    -0.06
    EVENT
    -0.06
     circumference
    -0.06
     Compass
    -0.06
    ging
    -0.06
     ymin
    -0.06
     DAC
    -0.06
    imizer
    -0.06
    (tk
    -0.06
    .eng
    -0.06
    POSITIVE LOGITS
     breat
    0.07
    Acknowled
    0.07
    _hdr
    0.07
    ‌دهد
    0.07
    _CTX
    0.06
    >>>>
    0.06
    _cos
    0.06
     کودکان
    0.06
    .vstack
    0.06
     Championship
    0.06
    Act Density 0.065%

    No Known Activations