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

    Neuronpedia

    INDEX
    Explanations

    cribe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equivalent
    -0.08
    şe
    -0.08
     Ged
    -0.07
     Voraussetzungen
    -0.07
    Calories
    -0.07
     tad
    -0.07
    (Store
    -0.07
     Infant
    -0.07
     insign
    -0.07
     insuf
    -0.07
    POSITIVE LOGITS
    prin
    0.08
     mindful
    0.07
     Julius
    0.07
    contract
    0.07
    nj
    0.07
    בנ
    0.07
     deler
    0.07
     בכ
    0.07
     CZ
    0.07
     nako
    0.07
    Act Density 0.001%

    No Known Activations