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

    Neuronpedia

    INDEX
    Explanations

    concerns about size, infidelity, gut feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ble
    0.40
     controvers
    0.40
     Vide
    0.39
     Не
    0.38
     když
    0.38
     prognostic
    0.38
     έγ
    0.38
     procès
    0.38
     Nachricht
    0.37
    ErrorBoundary
    0.37
    POSITIVE LOGITS
    bikes
    0.45
    。
    0.44
     BELOW
    0.43
     padassa
    0.42
    owym
    0.42
    below
    0.42
    Below
    0.41
    Ingredients
    0.41
    above
    0.41
    )।
    0.40
    Act Density 0.004%

    No Known Activations