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

    Neuronpedia

    INDEX
    Explanations

    likely completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     savor
    0.82
    KA
    0.77
    ന്‍
    0.75
    віта
    0.75
    তঃ
    0.73
    ウム
    0.73
     marah
    0.72
    aidl
    0.72
    ൻ
    0.72
    𝗹
    0.71
    POSITIVE LOGITS
     कराएंगे
    0.79
     procurement
    0.70
     sẽ
    0.69
    不會
    0.68
     Blanca
    0.68
     giành
    0.67
     hará
    0.67
     payer
    0.65
     смотрите
    0.65
     Será
    0.65
    Act Density 0.002%

    No Known Activations