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

    Neuronpedia

    INDEX
    Explanations

    Rome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Adventure
    -0.08
    拓展
    -0.08
    被困
    -0.07
     embark
    -0.07
    播种
    -0.07
     foes
    -0.06
     Bunny
    -0.06
     Gonz
    -0.06
    .equals
    -0.06
     buddy
    -0.06
    POSITIVE LOGITS
    データ
    0.07
    ㎕
    0.07
    utschen
    0.07
    loses
    0.07
    odynam
    0.07
    .first
    0.07
    个百分
    0.07
     mutable
    0.07
    procedure
    0.07
    etermin
    0.06
    Act Density 0.002%

    No Known Activations