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

    Neuronpedia

    INDEX
    Explanations

    Edge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aul
    -0.07
     hypnot
    -0.07
     CLAIM
    -0.07
    _plural
    -0.07
    NAL
    -0.07
    11
    -0.07
    05
    -0.07
    17
    -0.06
     Boston
    -0.06
    Avoid
    -0.06
    POSITIVE LOGITS
     Edge
    0.20
     edge
    0.19
    Edge
    0.18
     edges
    0.13
    EDGE
    0.12
     EDGE
    0.12
    -edge
    0.12
    .edge
    0.11
    edge
    0.11
    Edges
    0.09
    Act Density 0.012%

    No Known Activations