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

    Neuronpedia

    INDEX
    Explanations

    seems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ｀
    -0.07
    ành
    -0.07
     hàm
    -0.07
    �
    -0.07
    free
    -0.07
    ละเอ
    -0.07
    bite
    -0.07
     ус
    -0.07
     hình
    -0.06
    ôme
    -0.06
    POSITIVE LOGITS
     collapses
    0.06
     //////////////////
    0.06
    -cor
    0.06
    Tex
    0.06
     इसक
    0.06
     volunte
    0.06
     تز
    0.06
     إي
    0.06
     реги
    0.05
     EG
    0.05
    Act Density 0.149%

    No Known Activations