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

    Neuronpedia

    INDEX
    Explanations

    letter of recommendation for a teacher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্প
    1.90
     Rxe
    1.90
     Qxg
    1.89
     irony
    1.82
    ০
    1.78
    воз
    1.74
     amiss
    1.71
     quotid
    1.70
     logra
    1.60
     gerçekleşt
    1.59
    POSITIVE LOGITS
     भर
    1.54
     mendatang
    1.50
    iciency
    1.47
     remar
    1.45
    ال
    1.43
    सभी
    1.43
    গ
    1.42
    𝘥
    1.39
    ##############
    1.39
    ראל
    1.36
    Act Density 0.000%

    No Known Activations