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

    Neuronpedia

    INDEX
    Explanations

    is weathered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pursuant
    0.37
     using
    0.36
     scenarios
    0.36
     nhé
    0.35
     hoặc
    0.33
     använder
    0.33
     gameplay
    0.33
     menerapkan
    0.33
     onboarding
    0.32
     данного
    0.32
    POSITIVE LOGITS
     glistening
    0.41
     shimmering
    0.40
     gleaming
    0.39
     faintly
    0.38
     swollen
    0.37
     දු
    0.36
     trembling
    0.36
     spind
    0.35
     glittering
    0.35
     swirling
    0.35
    Act Density 0.818%

    No Known Activations