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

    Neuronpedia

    INDEX
    Explanations

    op

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abyss
    -0.06
    _WALL
    -0.06
    .djang
    -0.06
     çerç
    -0.06
    (Dictionary
    -0.06
     다시
    -0.06
    ilogy
    -0.06
    ường
    -0.06
    datas
    -0.05
    .byte
    -0.05
    POSITIVE LOGITS
    ほど
    0.07
     suppl
    0.07
    ED
    0.07
    990
    0.07
    婚
    0.06
    Previously
    0.06
    TEAM
    0.06
    0
    0.06
    _INV
    0.06
    رة
    0.06
    Act Density 0.001%

    No Known Activations