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

    Neuronpedia

    INDEX
    Explanations

    list of items as range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enthusiast
    0.86
    Signup
    0.83
    e
    0.82
    us
    0.82
    𝖎
    0.82
    Favourite
    0.81
      
    0.79
    Save
    0.79
     género
    0.79
     detenido
    0.78
    POSITIVE LOGITS
     результатов
    1.22
     результа
    1.14
    heses
    1.12
    entropic
    1.10
     hinges
    1.07
     numériques
    1.07
     простых
    1.07
     рамках
    1.06
     제시
    1.05
     gắn
    1.04
    Act Density 0.003%

    No Known Activations