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

    Neuronpedia

    INDEX
    Explanations

    Citation IDs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Texture
    -0.06
     que
    -0.06
        ↵    ↵    ↵
    -0.06
    ân
    -0.06
    renders
    -0.06
     Valencia
    -0.06
    Raised
    -0.06
     μετά
    -0.06
     orchestr
    -0.06
    Hung
    -0.06
    POSITIVE LOGITS
     предел
    0.07
     forgiveness
    0.07
    ابل
    0.07
     QRect
    0.06
     teardown
    0.06
    rstrip
    0.06
    urbation
    0.06
     AttributeError
    0.06
    しま
    0.06
    -lock
    0.06
    Act Density 0.022%

    No Known Activations