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

    Neuronpedia

    INDEX
    Explanations

    authorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sim
    -0.07
    $sub
    -0.07
     trab
    -0.07
     hx
    -0.07
    роме
    -0.07
     эту
    -0.06
    한
    -0.06
     аб
    -0.06
     vše
    -0.06
     tudo
    -0.06
    POSITIVE LOGITS
    (defun
    0.07
    atl
    0.06
    anz
    0.06
    urpose
    0.06
    agy
    0.06
    .Sprintf
    0.06
    _teacher
    0.06
     conse
    0.06
    ,ev
    0.06
     gul
    0.06
    Act Density 0.021%

    No Known Activations