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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wii
    -0.07
    قه
    -0.07
    .Conv
    -0.07
    یه
    -0.06
    akt
    -0.06
    baugh
    -0.06
     Eğitim
    -0.06
     yoga
    -0.06
    utz
    -0.06
    ENCIL
    -0.06
    POSITIVE LOGITS
     homelessness
    0.07
    ็นอ
    0.07
    .Team
    0.06
     velk
    0.06
    드리
    0.06
     Tyler
    0.06
     HttpServletResponse
    0.06
    dated
    0.06
     Models
    0.06
     popped
    0.06
    Act Density 0.022%

    No Known Activations