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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enjoy
    -0.07
    Metal
    -0.07
    strcmp
    -0.06
    quota
    -0.06
    .shuffle
    -0.06
     проти
    -0.06
    чаются
    -0.06
     Hizmet
    -0.06
    808
    -0.06
    <Order
    -0.06
    POSITIVE LOGITS
    .google
    0.07
    方法
    0.07
    (Controller
    0.07
    REATED
    0.07
    _ARCH
    0.07
    ทธ
    0.07
    RODUCTION
    0.06
     restau
    0.06
     Habitat
    0.06
    Xã
    0.06
    Act Density 0.005%

    No Known Activations