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

    Neuronpedia

    INDEX
    Explanations

    internet access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tercer
    -0.07
    gear
    -0.07
     crossover
    -0.07
     Olsen
    -0.07
     المص
    -0.06
     KAR
    -0.06
     swear
    -0.06
    sal
    -0.06
     chute
    -0.06
    USART
    -0.06
    POSITIVE LOGITS
    reply
    0.07
    ），
    0.07
    編
    0.06
     _↵↵
    0.06
     建
    0.06
     LE
    0.06
     پای
    0.06
     usado
    0.06
    _references
    0.06
     behaves
    0.06
    Act Density 0.005%

    No Known Activations