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

    Neuronpedia

    INDEX
    Explanations

    able to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    0.50
    ່ວນ
    0.49
    association
    0.48
    образие
    0.48
    알
    0.47
    introduction
    0.47
    same
    0.46
    ೫
    0.46
    eries
    0.46
    obedience
    0.46
    POSITIVE LOGITS
     bodied
    0.76
     able
    0.54
     withstand
    0.50
     to
    0.48
    bodied
    0.46
     successfully
    0.45
     Able
    0.43
    Able
    0.42
     afford
    0.40
     afforded
    0.39
    Act Density 0.010%

    No Known Activations