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

    Neuronpedia

    INDEX
    Explanations

    a list or count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.17
     avoir
    0.14
    อัต
    0.14
     extracting
    0.14
    বিভ
    0.14
     having
    0.14
     using
    0.13
    obytes
    0.13
    iskt
    0.13
     appears
    0.13
    POSITIVE LOGITS
     multitude
    0.22
     plethora
    0.19
     Vielzahl
    0.18
    ד
    0.18
    רי
    0.17
     myriad
    0.16
    스
    0.16
    티
    0.16
    с
    0.16
    ריה
    0.16
    Act Density 1.650%

    No Known Activations