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

    Neuronpedia

    INDEX
    Explanations

    confirm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    외
    -0.07
     County
    -0.07
     Observ
    -0.07
     Pod
    -0.07
     Libre
    -0.07
    immers
    -0.07
     Wür
    -0.07
     Observatory
    -0.07
     lont
    -0.07
     Suspension
    -0.07
    POSITIVE LOGITS
     пароль
    0.13
     senha
    0.13
    Password
    0.13
    _password
    0.12
    (password
    0.12
    .password
    0.12
    	password
    0.12
     PASSWORD
    0.12
     Password
    0.12
    password
    0.12
    Act Density 0.001%

    No Known Activations