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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obierno
    -0.07
    nard
    -0.06
     intend
    -0.06
     nurturing
    -0.06
     computation
    -0.06
    ンプ
    -0.06
     primaryStage
    -0.06
    σταν
    -0.06
     verir
    -0.06
    MOTE
    -0.06
    POSITIVE LOGITS
     năng
    0.07
    _CO
    0.07
     INS
    0.06
     touring
    0.06
    linewidth
    0.06
    .db
    0.06
     Occ
    0.06
    ……」↵↵
    0.06
    _CTRL
    0.06
    λλι
    0.06
    Act Density 0.002%

    No Known Activations