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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     understands
    -0.08
    _logged
    -0.07
    ([]
    -0.07
    (JSON
    -0.07
     Cheat
    -0.07
     intact
    -0.07
    �
    -0.06
     Tear
    -0.06
    (sp
    -0.06
    动态
    -0.06
    POSITIVE LOGITS
    PRESSION
    0.07
    浏览器
    0.07
    ôtel
    0.07
     Pistons
    0.07
    oplay
    0.06
    eler
    0.06
     Gamer
    0.06
    datal
    0.06
    降雨
    0.06
    pedido
    0.06
    Act Density 0.039%

    No Known Activations