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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ReSharper
    -0.07
     SUR
    -0.07
     Esther
    -0.07
     Reynolds
    -0.06
    GBT
    -0.06
    FER
    -0.06
     فرو
    -0.06
     sarc
    -0.06
    ¬
    -0.06
     در
    -0.06
    POSITIVE LOGITS
    0.08
    0.07
    0.07
    0.07
     Associate
    0.07
    0.07
    0.07
    0.07
    0.07
    0.07
    Act Density 0.044%

    No Known Activations