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

    Neuronpedia

    INDEX
    Explanations

    error handling except catch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इतर
    0.45
    '.
    0.40
    cyte
    0.39
     لط
    0.38
    🚃
    0.38
    
    0.38
     اختيار
    0.38
     Infection
    0.37
    瀆
    0.37
     अप्र
    0.36
    POSITIVE LOGITS
     bhikkhave
    0.42
     cts
    0.40
     CALL
    0.39
    except
    0.38
     emphasized
    0.38
     относи
    0.38
     PHONE
    0.38
     CENTRE
    0.37
     tallied
    0.37
     empezó
    0.37
    Act Density 0.082%

    No Known Activations