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

    Neuronpedia

    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,map
    -0.07
    cepts
    -0.07
    _return
    -0.07
    ظر
    -0.07
    듈
    -0.07
    投入
    -0.07
    商机
    -0.07
    饱和
    -0.06
    怀抱
    -0.06
    /pass
    -0.06
    POSITIVE LOGITS
    Kate
    0.07
     citation
    0.07
    Legendary
    0.07
    ----↵
    0.07
    𬭯
    0.07
     celebrities
    0.07
    ᗩ
    0.07
    ombies
    0.07
    好朋友
    0.07
    쎈
    0.07
    Act Density 0.002%

    No Known Activations