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

    Neuronpedia

    INDEX
    Explanations

    connected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (nd
    -0.07
     Bak
    -0.06
    112
    -0.06
     toddler
    -0.06
     beetle
    -0.06
    рити
    -0.06
    한국
    -0.06
     κι
    -0.06
    829
    -0.06
     lazy
    -0.06
    POSITIVE LOGITS
     connected
    0.07
     illuminated
    0.07
     비
    0.07
    oref
    0.07
    touches
    0.07
    Measured
    0.06
     bottleneck
    0.06
    ($('.
    0.06
     connect
    0.06
    gether
    0.06
    Act Density 0.032%

    No Known Activations