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

    Neuronpedia

    INDEX
    Explanations

    connections and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thanking
    0.49
     teşekkür
    0.48
     Amazing
    0.48
     Charan
    0.47
     gesturing
    0.46
     antlers
    0.45
     ulcerative
    0.44
     Deccan
    0.44
     intends
    0.43
     amazing
    0.43
    POSITIVE LOGITS
    Zo
    0.43
    ρή
    0.42
     triángulo
    0.41
     vendido
    0.40
     purch
    0.40
    equal
    0.40
    쭈
    0.39
    Surf
    0.39
    isol
    0.39
    Productos
    0.39
    Act Density 0.002%

    No Known Activations