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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ropdown
    -0.07
     부분
    -0.07
    _robot
    -0.07
    aternion
    -0.07
     non
    -0.06
    _mesh
    -0.06
    sword
    -0.06
    _pv
    -0.06
     descripcion
    -0.06
    'in
    -0.06
    POSITIVE LOGITS
     subtle
    0.07
     Stef
    0.07
     FRE
    0.06
    _ORIENTATION
    0.06
    (Point
    0.06
     Получ
    0.06
    489
    0.06
    ANTED
    0.06
    ega
    0.06
    bler
    0.06
    Act Density 0.016%

    No Known Activations