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

    Neuronpedia

    INDEX
    Explanations

    how to make or do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fragment
    0.25
     عبر
    0.23
    path
    0.23
    numeric
    0.23
    ave
    0.23
    linear
    0.23
    adv
    0.23
    3
    0.23
    diagonal
    0.22
    )^
    0.22
    POSITIVE LOGITS
     такой
    0.25
     peces
    0.24
    却没有
    0.24
     такого
    0.24
     quilts
    0.23
     udrž
    0.23
     aliments
    0.23
     this
    0.23
     있지만
    0.23
     ilyen
    0.23
    Act Density 0.183%

    No Known Activations