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

    Neuronpedia

    INDEX
    Explanations

    Greek letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bounds
    -0.08
    Coal
    -0.07
    Driving
    -0.07
     bilder
    -0.07
    旧
    -0.06
    Convertible
    -0.06
    Drawing
    -0.06
     Folk
    -0.06
     finder
    -0.06
     NZ
    -0.06
    POSITIVE LOGITS
    654
    0.07
     ");↵
    0.06
    ức
    0.06
     Edgar
    0.06
    _%
    0.06
    147
    0.06
    :"",↵
    0.06
    olumn
    0.06
     Bian
    0.06
    لاق
    0.06
    Act Density 0.005%

    No Known Activations