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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ゴ
    -0.07
    issan
    -0.07
    pq
    -0.06
     webpage
    -0.06
    _test
    -0.06
    _final
    -0.06
     SUMMARY
    -0.06
    series
    -0.06
     larvae
    -0.06
    言葉
    -0.06
    POSITIVE LOGITS
     IK
    0.06
    ane
    0.06
     علي
    0.06
    ریف
    0.06
     Greenwood
    0.06
    .N
    0.06
     외국
    0.06
     persön
    0.05
    场
    0.05
     RN
    0.05
    Act Density 0.009%

    No Known Activations