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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ruby
    -0.07
    σί
    -0.06
    CTest
    -0.06
    (sol
    -0.06
    _Save
    -0.06
    росто
    -0.06
     YYYY
    -0.06
    asje
    -0.06
     Telescope
    -0.06
    /li
    -0.06
    POSITIVE LOGITS
    wie
    0.07
    (Thread
    0.06
     eagerly
    0.06
     deciding
    0.06
     foregoing
    0.06
     заходів
    0.06
     MLA
    0.06
     slang
    0.06
    Gre
    0.06
     filed
    0.06
    Act Density 0.005%

    No Known Activations