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

    Neuronpedia

    INDEX
    Explanations

    sentence continuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸Ģçĵ¶
    -0.29
    ertia
    -0.27
    éĩį
    -0.26
    å½ĵçĦ¶
    -0.26
     Convenient
    -0.26
    æ²ī
    -0.25
     пÑĢоб
    -0.25
    磨
    -0.25
    пÑĢод
    -0.24
    áºĵ
    -0.24
    POSITIVE LOGITS
    ctions
    0.28
    emente
    0.27
    ction
    0.27
    amac
    0.26
    xic
    0.25
    æł·å¼ı
    0.25
    rek
    0.25
    ally
    0.24
    IID
    0.24
    绾
    0.24
    Act Density 0.698%

    No Known Activations