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

    Neuronpedia

    INDEX
    Explanations

    .Web

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DX
    -0.07
    atLng
    -0.07
    quisa
    -0.07
    jez
    -0.06
    ρια
    -0.06
    Tiles
    -0.06
    пня
    -0.06
    ignite
    -0.06
    attle
    -0.06
     Knoxville
    -0.06
    POSITIVE LOGITS
    .Web
    0.12
     Web
    0.07
    heed
    0.07
    b
    0.07
    _sig
    0.06
     Анд
    0.06
    sorting
    0.06
    Neill
    0.06
     Wheel
    0.06
    'Neill
    0.06
    Act Density 0.001%

    No Known Activations