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

    Neuronpedia

    INDEX
    Explanations

    that followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.37
    e
    0.35
    ع
    0.35
    ur
    0.35
    ви
    0.34
    的
    0.34
    ва
    0.33
    чи
    0.33
    ї
    0.33
    0.32
    POSITIVE LOGITS
    t
    0.55
    3
    0.49
    ties
    0.47
    4
    0.44
    tica
    0.40
    tl
    0.38
    ों
    0.38
    tosecond
    0.38
    ין
    0.37
    tions
    0.36
    Act Density 0.107%

    No Known Activations