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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slam
    -0.07
     放
    -0.07
    Raise
    -0.06
    κη
    -0.06
    seeing
    -0.06
    経
    -0.06
    洪
    -0.06
     bev
    -0.06
    ین
    -0.06
     znění
    -0.06
    POSITIVE LOGITS
     %↵
    0.07
    !!!↵
    0.06
     desire
    0.06
     emailed
    0.06
    .req
    0.06
    .must
    0.06
     اگر
    0.06
    [])↵
    0.05
    ягом
    0.05
    LENGTH
    0.05
    Act Density 0.000%

    No Known Activations