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

    Neuronpedia

    INDEX
    Explanations

    beating or shaping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BC
    -0.07
     Young
    -0.06
    socket
    -0.06
    \Core
    -0.06
    ously
    -0.06
    Bush
    -0.06
    height
    -0.06
     Shopping
    -0.06
    𬳶
    -0.06
     dark
    -0.06
    POSITIVE LOGITS
    人社局
    0.07
     существует
    0.07
    _STRIP
    0.07
    دت
    0.07
    urile
    0.07
    った
    0.06
    .Live
    0.06
    ��
    0.06
     fred
    0.06
    RIX
    0.06
    Act Density 0.034%

    No Known Activations