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

    Neuronpedia

    INDEX
    Explanations

    categories of places/people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employees
    -0.07
    >t
    -0.07
     astonished
    -0.07
    }.
    -0.06
     creator
    -0.06
     confirms
    -0.06
     backstory
    -0.06
     remember
    -0.06
     crem
    -0.06
     Dialogue
    -0.06
    POSITIVE LOGITS
    -Aug
    0.07
    brıs
    0.06
    inci
    0.06
    .slug
    0.06
    chyb
    0.06
    Frameworks
    0.06
    ýn
    0.06
     fisse
    0.06
    ceb
    0.06
    냐
    0.06
    Act Density 0.074%

    No Known Activations