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

    Neuronpedia

    INDEX
    Explanations

    Data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cellphone
    -0.07
    烊
    -0.07
     조직
    -0.07
    ﯹ
    -0.07
     API
    -0.07
     المنطقة
    -0.06
    包装
    -0.06
    ennent
    -0.06
     mismatch
    -0.06
    Enterprise
    -0.06
    POSITIVE LOGITS
    career
    0.07
     bądź
    0.07
    显然是
    0.07
    InstanceId
    0.07
    FTER
    0.07
     rv
    0.07
    .Paint
    0.07
    斥
    0.07
     psychiatrist
    0.06
    oused
    0.06
    Act Density 0.080%

    No Known Activations