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

    Neuronpedia

    INDEX
    Explanations

    United

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Checklist
    -0.07
    카
    -0.07
    trap
    -0.06
    -around
    -0.06
    _fg
    -0.06
     ä
    -0.06
     Arbor
    -0.06
     Spear
    -0.06
    494
    -0.06
    sip
    -0.06
    POSITIVE LOGITS
     United
    0.08
     ConfigureServices
    0.08
    люч
    0.07
     未
    0.07
    ियल
    0.07
     deduct
    0.07
    ㅠㅠ
    0.07
     CreateUser
    0.07
    ㄷ
    0.07
    -
↵
    0.06
    Act Density 0.029%

    No Known Activations