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

    Neuronpedia

    INDEX
    Explanations

    details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (stack
    -0.07
    Request
    -0.07
     restarted
    -0.06
     dün
    -0.06
    (site
    -0.06
     beaches
    -0.06
    和
    -0.06
     connection
    -0.06
     request
    -0.06
     Request
    -0.06
    POSITIVE LOGITS
    ائي
    0.07
     barr
    0.06
    BOOLE
    0.06
     inexperienced
    0.06
    xAC
    0.06
     minimalist
    0.06
     потом
    0.06
    微笑
    0.06
    勇
    0.06
    ensem
    0.06
    Act Density 0.011%

    No Known Activations