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

    Neuronpedia

    INDEX
    Explanations

    breeds and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üksek
    0.80
     soov
    0.78
     последнего
    0.76
    High
    0.71
     High
    0.69
     warts
    0.68
     высокая
    0.68
     해외
    0.67
     Thackeray
    0.67
     vakar
    0.67
    POSITIVE LOGITS
     renamed
    0.82
    agara
    0.82
     নামে
    0.81
     أي
    0.77
    任何
    0.77
     ఆది
    0.77
    âmb
    0.76
    ésére
    0.75
     জানিতে
    0.74
    abeled
    0.73
    Act Density 0.596%

    No Known Activations