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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    veh
    -0.07
    自信
    -0.07
    .RowIndex
    -0.07
    天下
    -0.07
    (currency
    -0.07
    erosis
    -0.07
    طي
    -0.07
    .arc
    -0.06
    新冠疫情
    -0.06
     knex
    -0.06
    POSITIVE LOGITS
     Hond
    0.07
     straps
    0.06
     portraits
    0.06
     formulated
    0.06
    -variable
    0.06
     추진
    0.06
    oreal
    0.06
    odox
    0.06
    �
    0.06
     Ra
    0.06
    Act Density 0.010%

    No Known Activations