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

    Neuronpedia

    INDEX
    Explanations

    :-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collect
    -0.07
     return
    -0.06
     메
    -0.06
    NEWS
    -0.06
    (login
    -0.06
    (de
    -0.06
     rifles
    -0.06
     PROGRAM
    -0.06
    від
    -0.06
     Chrome
    -0.06
    POSITIVE LOGITS
    aging
    0.08
     utiliz
    0.07
    ats
    0.07
     kredi
    0.07
    .commit
    0.07
     clarify
    0.06
    however
    0.06
     этому
    0.06
     اروپا
    0.06
     blinked
    0.06
    Act Density 0.002%

    No Known Activations