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

    Neuronpedia

    INDEX
    Explanations

    bio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uth
    -0.07
    Yaw
    -0.07
     xấu
    -0.07
    _HTML
    -0.07
    }')
    -0.06
     Saud
    -0.06
    leaders
    -0.06
     Facial
    -0.06
     invo
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Registry
    0.06
     salute
    0.06
     holy
    0.06
    バイ
    0.06
     sk
    0.06
     glad
    0.06
     日
    0.06
    esk
    0.06
    ск
    0.06
    userId
    0.06
    Act Density 0.000%

    No Known Activations