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

    Neuronpedia

    INDEX
    Explanations

    small quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ography
    -0.07
    _logger
    -0.06
    єн
    -0.06
     cohesion
    -0.06
     Sparse
    -0.06
     Rogers
    -0.06
    τό
    -0.06
    rus
    -0.06
    ATFORM
    -0.06
    _year
    -0.06
    POSITIVE LOGITS
     Wow
    0.07
     gibt
    0.07
     brill
    0.07
    ��
    0.07
     Bere
    0.06
    Α
    0.06
     پیش
    0.06
    (GLFW
    0.06
    íme
    0.06
     Saw
    0.06
    Act Density 0.023%

    No Known Activations