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

    Neuronpedia

    INDEX
    Explanations

    Hello, World! code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ణాలు
    0.86
    ectors
    0.84
    示す
    0.82
    َّا
    0.81
    closure
    0.79
    ణ
    0.79
    VIII
    0.79
    ixes
    0.78
    هرة
    0.78
    Tourist
    0.77
    POSITIVE LOGITS
     unglaublich
    1.06
     blockchains
    1.04
     parceria
    1.03
     blockchain
    1.00
     alpin
    1.00
     bastion
    0.99
     revolutionized
    0.98
     DevOps
    0.97
     revolución
    0.97
     אל
    0.96
    Act Density 0.019%

    No Known Activations