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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circuit
    -0.08
    arna
    -0.08
     Circuit
    -0.07
    -circle
    -0.07
    -hi
    -0.07
    -house
    -0.07
     cooling
    -0.07
     Cooling
    -0.07
     dédié
    -0.07
     dedicado
    -0.07
    POSITIVE LOGITS
     വന്ന
    0.10
     జరిగిన
    0.09
     inesper
    0.08
     സംഭവ
    0.08
    され
    0.08
     ഇവ
    0.08
     Zheng
    0.08
    incoming
    0.08
     നടന്ന
    0.08
     принес
    0.08
    Act Density 0.007%

    No Known Activations