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

    Neuronpedia

    INDEX
    Explanations

    physical properties and chemical reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мире
    0.44
    teilung
    0.44
    world
    0.42
    sorry
    0.42
     Hartley
    0.42
    世界的
    0.41
     mundo
    0.41
    World
    0.41
    Worlds
    0.41
    giphy
    0.41
    POSITIVE LOGITS
     substituted
    0.45
     UEFA
    0.39
     portfolios
    0.38
     variable
    0.38
     undertakings
    0.38
     disclosing
    0.38
    ➖
    0.38
     RPM
    0.37
     Hypot
    0.37
     גבוה
    0.37
    Act Density 0.001%

    No Known Activations