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

    Neuronpedia

    INDEX
    Explanations

    compared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    培训机构
    -0.07
    暇
    -0.07
    贫困村
    -0.07
    露
    -0.07
    镧
    -0.07
    鹮
    -0.07
     apresent
    -0.07
     Proposition
    -0.07
    골
    -0.07
     deserving
    -0.06
    POSITIVE LOGITS
    _exact
    0.09
    하시
    0.08
     текст
    0.07
     settlers
    0.07
    asi
    0.07
    افة
    0.07
     cues
    0.07
     coeff
    0.06
    غني
    0.06
     bo
    0.06
    Act Density 0.804%

    No Known Activations