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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contractors
    -0.07
    missive
    -0.07
    Separated
    -0.06
    {}↵↵
    -0.06
    Thirty
    -0.06
    urban
    -0.06
     tinder
    -0.06
    cta
    -0.06
     donne
    -0.06
     Cou
    -0.06
    POSITIVE LOGITS
    675
    0.06
    香
    0.06
    くだ
    0.06
    walking
    0.06
     используется
    0.06
     사이
    0.06
    tl
    0.06
    �
    0.06
    sbin
    0.06
    .calendar
    0.06
    Act Density 0.000%

    No Known Activations