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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ḳ
    -0.07
     financially
    -0.07
     aprove
    -0.07
     Messiah
    -0.07
     acknow
    -0.07
    首轮
    -0.07
    �
    -0.06
    ้อน
    -0.06
     ú
    -0.06
    arness
    -0.06
    POSITIVE LOGITS
    cott
    0.07
     PF
    0.07
    CVE
    0.07
     atlas
    0.07
     TLC
    0.07
     resil
    0.07
    slider
    0.07
    ть
    0.06
     entrega
    0.06
    (cert
    0.06
    Act Density 0.056%

    No Known Activations