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

    Neuronpedia

    INDEX
    Explanations

    CR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    謝
    -0.07
    Survey
    -0.07
     sacked
    -0.07
    שמת
    -0.07
     rollout
    -0.06
     Thư
    -0.06
     slides
    -0.06
     tightly
    -0.06
    减速
    -0.06
    踏
    -0.06
    POSITIVE LOGITS
    괴
    0.07
    .CV
    0.07
    首届
    0.07
    (K
    0.07
     Mong
    0.07
    .Env
    0.07
    حساب
    0.07
    _COMPONENT
    0.07
    ويل
    0.07
     honour
    0.06
    Act Density 0.113%

    No Known Activations