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

    Neuronpedia

    INDEX
    Explanations

    accessing API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     интерфей
    0.47
     Interface
    0.45
     Rau
    0.45
     Quindi
    0.44
    grandfather
    0.44
    🔎
    0.44
    geographic
    0.44
    停
    0.44
    🧿
    0.43
    ostomy
    0.43
    POSITIVE LOGITS
     awakening
    0.51
     vector
    0.51
     levers
    0.50
     worms
    0.50
     awakens
    0.49
     watts
    0.48
     shaders
    0.47
     gris
    0.47
     gliding
    0.46
     waking
    0.46
    Act Density 0.002%

    No Known Activations