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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Helpers
    -0.08
    ��
    -0.08
     приобрести
    -0.08
     Gara
    -0.08
    .Na
    -0.08
    ಪ್
    -0.07
     covering
    -0.07
    cult
    -0.07
    યો
    -0.07
     couvrir
    -0.07
    POSITIVE LOGITS
     že
    0.08
    —and
    0.07
    maker
    0.07
     cho
    0.07
     diferenci
    0.07
    ���
    0.07
    Rh
    0.07
     Cru
    0.07
     Khan
    0.07
     minas
    0.07
    Act Density 0.303%

    No Known Activations