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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bidden
    -0.06
    BEST
    -0.06
    /request
    -0.06
     Increment
    -0.06
     rental
    -0.06
     newIndex
    -0.06
    _tag
    -0.06
    _Local
    -0.06
    .gg
    -0.06
     clergy
    -0.06
    POSITIVE LOGITS
     ＼↵
    0.07
    ＼↵
    0.06
     Tanz
    0.06
    were
    0.06
    하였
    0.06
    .star
    0.06
     krij
    0.06
     структур
    0.06
    zim
    0.06
     μη
    0.06
    Act Density 0.001%

    No Known Activations