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

    Neuronpedia

    INDEX
    Explanations

    pronouns and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ö
    -0.09
     makeup
    -0.07
    рош
    -0.07
     జరుగ
    -0.07
    �
    -0.07
     abnormal
    -0.07
     ನಡೆಯ
    -0.07
     reboot
    -0.07
     bereid
    -0.07
     preprocess
    -0.07
    POSITIVE LOGITS
     wajen
    0.10
     để
    0.10
     reliably
    0.10
     Gelegenheit
    0.08
     wisely
    0.08
     بطريقة
    0.08
     creatively
    0.08
     guía
    0.08
     Ordin
    0.08
    來
    0.08
    Act Density 0.070%

    No Known Activations