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

    Neuronpedia

    INDEX
    Explanations

    frame concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಕೊಟ್ಟ
    0.44
    flat
    0.41
     satellite
    0.39
    prefix
    0.38
    brown
    0.38
    satellite
    0.38
    funded
    0.38
    пло
    0.37
    themed
    0.37
    splitting
    0.37
    POSITIVE LOGITS
     Frame
    1.08
     frame
    1.07
     frames
    1.04
     çerçe
    1.03
     Framing
    0.99
     framing
    0.97
    FRAM
    0.97
     FRAME
    0.93
     FRAM
    0.93
    Fram
    0.92
    Act Density 0.017%

    No Known Activations