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

    Neuronpedia

    INDEX
    Explanations

    percentages and shares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Van
    -0.08
    .addEdge
    -0.07
     CHECK
    -0.07
    臧
    -0.07
     "^
    -0.07
    JJ
    -0.07
    뚱
    -0.07
     Given
    -0.07
    омн
    -0.06
    ivant
    -0.06
    POSITIVE LOGITS
    )':
    0.07
    -area
    0.07
     frem
    0.07
    -<?
    0.07
    ʈ
    0.07
    Experimental
    0.07
    _special
    0.07
     wyłącznie
    0.07
    ᶻ
    0.07
    我没有
    0.07
    Act Density 0.045%

    No Known Activations