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

    Neuronpedia

    INDEX
    Explanations

    data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mate
    -0.07
     Oh
    -0.07
     bella
    -0.06
    ůl
    -0.06
    -wh
    -0.06
     morals
    -0.06
    Nr
    -0.06
     پرد
    -0.06
     cộng
    -0.06
    .Annotations
    -0.06
    POSITIVE LOGITS
    .ge
    0.06
     каб
    0.06
    *)↵
    0.06
     Вид
    0.06
    0.06
    rowing
    0.06
    ensely
    0.06
     subsidized
    0.06
    кое
    0.06
     движ
    0.05
    Act Density 0.034%

    No Known Activations