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

    Neuronpedia

    INDEX
    Explanations

    beginning of articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     easier
    -0.07
     further
    -0.06
    ..↵
    -0.06
     köz
    -0.06
     coin
    -0.06
     fortunate
    -0.06
    进一步
    -0.06
     jiného
    -0.06
    ฟอร
    -0.06
     youngest
    -0.06
    POSITIVE LOGITS
    /send
    0.07
    phans
    0.06
    ols
    0.06
    uib
    0.06
     santé
    0.06
    čku
    0.06
     Tanrı
    0.06
    riage
    0.06
     hearing
    0.06
    .workspace
    0.06
    Act Density 0.130%

    No Known Activations