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

    Neuronpedia

    INDEX
    Explanations

    first/second person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .kwargs
    -0.07
     mou
    -0.06
     Balanced
    -0.06
    .Done
    -0.06
    —with
    -0.06
     баз
    -0.06
     Austria
    -0.06
     lui
    -0.06
    蜜
    -0.06
     derechos
    -0.06
    POSITIVE LOGITS
     поп
    0.08
    .scal
    0.07
     McLaren
    0.07
    ова
    0.07
     Kramer
    0.07
    fluence
    0.06
     Shark
    0.06
     Valentine
    0.06
    848
    0.06
    Parameter
    0.06
    Act Density 0.080%

    No Known Activations