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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    staff
    -0.06
     flare
    -0.06
    retch
    -0.06
     ضر
    -0.06
    uter
    -0.06
    acob
    -0.06
     ruth
    -0.06
    ecn
    -0.06
    .(
    -0.06
     afl
    -0.06
    POSITIVE LOGITS
     btn
    0.07
    )):↵
    0.06
    PreferredGap
    0.06
    FML
    0.06
     />)↵
    0.06
     ))↵
    0.06
     ре
    0.06
    oplevel
    0.06
     Más
    0.06
     Але
    0.06
    Act Density 0.001%

    No Known Activations