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

    Neuronpedia

    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cname
    -0.08
     Device
    -0.07
     employ
    -0.07
    致电
    -0.07
    主動註冊
    -0.07
     Exist
    -0.07
    ("
    -0.07
    걜
    -0.07
    .in
    -0.06
     Admin
    -0.06
    POSITIVE LOGITS
    $I
    0.07
     gradu
    0.07
    _draft
    0.07
    お互
    0.07
     ?.
    0.07
    _WORLD
    0.07
    __)
    0.07
    egral
    0.07
    …but
    0.07
    脾
    0.07
    Act Density 0.007%

    No Known Activations