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

    Neuronpedia

    INDEX
    Explanations

    explaining "or" and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WILLIAM
    0.49
     bởi
    0.45
     karya
    0.42
     seconda
    0.42
     persones
    0.42
    𒁀
    0.42
    роваться
    0.41
     febrero
    0.41
     mempel
    0.40
    த்திலும்
    0.40
    POSITIVE LOGITS
     How
    0.45
     The
    0.43
    How
    0.42
    }]
    0.41
     how
    0.41
     Over
    0.41
     איך
    0.41
    什么是
    0.38
    全体の
    0.38
    })
    0.38
    Act Density 0.000%

    No Known Activations