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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Negative
    -0.07
     Victor
    -0.07
     Staff
    -0.07
     economy
    -0.06
    isEmpty
    -0.06
     Budget
    -0.06
     wrap
    -0.06
     Knife
    -0.06
    /groups
    -0.06
     Aren
    -0.06
    POSITIVE LOGITS
     vas
    0.06
    ایط
    0.06
     administer
    0.06
    nem
    0.06
    ЙЙ
    0.06
     تج
    0.06
    dain
    0.06
     bourgeois
    0.06
     ;;↵
    0.06
    (LOG
    0.06
    Act Density 0.005%

    No Known Activations