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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🍀
    -0.08
     RU
    -0.08
     disrupted
    -0.08
    隔壁
    -0.07
     Ok
    -0.07
    @Table
    -0.07
    .setMaximum
    -0.07
    sun
    -0.07
    这里是
    -0.07
     allies
    -0.07
    POSITIVE LOGITS
     가운데
    0.07
    ％
    0.07
    调查
    0.07
     Lloyd
    0.07
     pla
    0.07
     יית
    0.06
     Oczy
    0.06
     trustees
    0.06
     presenta
    0.06
    𫞩
    0.06
    Act Density 0.021%

    No Known Activations