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

    Neuronpedia

    INDEX
    Explanations

    light exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ใหม
    -0.07
     večer
    -0.06
     cuis
    -0.06
     expresses
    -0.06
     BET
    -0.06
     auc
    -0.06
     mig
    -0.06
     cropped
    -0.06
     SEE
    -0.06
     recebe
    -0.06
    POSITIVE LOGITS
    TV
    0.07
    0.07
     forControlEvents
    0.06
    طبي
    0.06
    ampling
    0.06
    豪
    0.06
     dood
    0.06
     전문
    0.06
    onation
    0.06
    (fig
    0.06
    Act Density 0.003%

    No Known Activations