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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accepting
    -0.07
    デ
    -0.06
    塔
    -0.06
    لیم
    -0.06
     tamam
    -0.06
    nas
    -0.06
    διά
    -0.06
    unto
    -0.06
    autor
    -0.06
    ίδα
    -0.06
    POSITIVE LOGITS
     SECURITY
    0.07
     دستور
    0.06
     급
    0.06
    imary
    0.06
    (grammar
    0.06
     hardcore
    0.06
     concess
    0.06
    (Http
    0.06
     UserProfile
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations