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

    Neuronpedia

    INDEX
    Explanations

    timecodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আবশ্যক
    0.40
     billions
    0.38
    geq
    0.38
     computations
    0.37
    recer
    0.37
     burl
    0.37
     wigs
    0.37
     subprocess
    0.36
    aidl
    0.36
     वेरिए
    0.35
    POSITIVE LOGITS
     minute
    1.20
     minuto
    1.16
     Minute
    1.10
    Minute
    1.09
    minute
    1.09
     मिनट
    0.99
     minutes
    0.98
    分钟
    0.98
     minutos
    0.96
    minutes
    0.94
    Act Density 0.027%

    No Known Activations