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

    Neuronpedia

    INDEX
    Explanations

    software installation or updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -----
    -0.07
    ...)
    -0.07
     mulheres
    -0.06
    User
    -0.06
     escorte
    -0.06
     mange
    -0.06
     dow
    -0.06
     directing
    -0.06
    Daniel
    -0.06
     lovers
    -0.06
    POSITIVE LOGITS
    brace
    0.07
     nướng
    0.06
    alance
    0.06
     число
    0.06
     PR
    0.06
    ΑΓ
    0.06
    �
    0.06
    :"
    0.06
    .isAdmin
    0.06
    _logits
    0.06
    Act Density 0.105%

    No Known Activations