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

    Neuronpedia

    INDEX
    Explanations

    resist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vä
    -0.07
     ổ
    -0.07
    XP
    -0.07
    di
    -0.07
    讀
    -0.07
    com
    -0.07
    奔
    -0.07
    translated
    -0.06
     בעצ
    -0.06
    速度
    -0.06
    POSITIVE LOGITS
    される
    0.08
     Tanner
    0.08
    떪
    0.07
     Nexus
    0.07
    なぁ
    0.07
    /span
    0.07
     regulation
    0.07
    _Login
    0.07
     Claw
    0.07
    follower
    0.07
    Act Density 0.012%

    No Known Activations