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

    Neuronpedia

    INDEX
    Explanations

    ==

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elections
    -0.08
    AUDIO
    -0.07
    �
    -0.07
    伊斯
    -0.07
     Abdullah
    -0.06
    IconModule
    -0.06
    DataTask
    -0.06
     Battalion
    -0.06
     kilomet
    -0.06
    プリン
    -0.06
    POSITIVE LOGITS
     qualifications
    0.06
    双边
    0.06
    	restore
    0.06
    nat
    0.06
    มาตรฐาน
    0.06
    中药
    0.06
    aida
    0.06
    处
    0.06
     формы
    0.06
     стоит
    0.06
    Act Density 0.001%

    No Known Activations