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

    Neuronpedia

    INDEX
    Explanations

    mathematical and logical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assort
    -0.08
     τέ
    -0.07
     aici
    -0.07
     сдел
    -0.07
     вчера
    -0.07
    .Tech
    -0.07
     assortment
    -0.07
     நல்ல
    -0.07
     жар
    -0.07
     기사
    -0.07
    POSITIVE LOGITS
     Glue
    0.10
    直到
    0.09
    wards
    0.08
    逐
    0.08
    Until
    0.07
    遇
    0.07
     backwards
    0.07
     Blanche
    0.07
     greed
    0.07
    .at
    0.07
    Act Density 0.014%

    No Known Activations