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
     societies
    -0.07
     Courts
    -0.07
    št
    -0.07
    Cart
    -0.07
    神
    -0.06
    usta
    -0.06
     chapters
    -0.06
    _cost
    -0.06
     courts
    -0.06
     schema
    -0.06
    POSITIVE LOGITS
     principales
    0.06
     державної
    0.06
    каж
    0.06
     Isabel
    0.05
    inations
    0.05
     jenter
    0.05
     initializing
    0.05
    Initializing
    0.05
     الأمريكية
    0.05
    energy
    0.05
    Act Density 0.003%

    No Known Activations