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

    Neuronpedia

    INDEX
    Explanations

    foreign language indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disability
    0.50
     disabilities
    0.44
     discre
    0.42
     bandages
    0.42
     bonds
    0.42
     expectations
    0.41
     adhesion
    0.41
     distortions
    0.41
     glutathione
    0.41
     pregi
    0.41
    POSITIVE LOGITS
    нт
    0.47
     للمعارف
    0.47
    ф
    0.45
    mLogin
    0.45
    ilingual
    0.44
    ooled
    0.42
    оте
    0.41
    Cuenta
    0.41
    с
    0.41
    alai
    0.40
    Act Density 3.981%

    No Known Activations