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

    Neuronpedia

    INDEX
    Explanations

    crucial, crucially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correctement
    0.68
    ations
    0.65
    ration
    0.65
    вання
    0.63
    isierung
    0.62
     correctly
    0.61
    ersion
    0.60
     सफलतापूर्वक
    0.60
     successfully
    0.60
    ování
    0.59
    POSITIVE LOGITS
    cially
    1.38
    ially
    1.15
    inally
    1.08
    icial
    1.04
    ifically
    1.04
    ialmente
    1.03
    icially
    1.02
    cial
    0.99
    ually
    0.97
    적으로
    0.97
    Act Density 0.298%

    No Known Activations