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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уса
    -0.07
     rivals
    -0.07
     pots
    -0.06
    eson
    -0.06
    oving
    -0.06
     loyal
    -0.06
    .argsort
    -0.06
     flo
    -0.06
     ancor
    -0.06
    _Login
    -0.06
    POSITIVE LOGITS
     політи
    0.06
     při
    0.06
     genellikle
    0.06
     porrf
    0.06
     slou
    0.06
    Dispose
    0.06
     Monkey
    0.06
     protester
    0.06
     никто
    0.06
    Monkey
    0.06
    Act Density 0.016%

    No Known Activations