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

    Neuronpedia

    INDEX
    Explanations

    gradual increase in activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们将
    0.52
     naszego
    0.46
    无论是
    0.45
     наших
    0.45
     наши
    0.44
    ның
    0.44
     our
    0.43
     нашего
    0.43
     нашу
    0.43
    也将
    0.43
    POSITIVE LOGITS
     diuretics
    0.50
     supernatant
    0.49
     polymerase
    0.47
     subtypes
    0.47
     isotonic
    0.47
     dopo
    0.46
     intermittently
    0.46
     after
    0.46
     vasodil
    0.46
     polysaccharide
    0.46
    Act Density 0.001%

    No Known Activations