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

    Neuronpedia

    INDEX
    Explanations

    after or during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нужны
    1.20
     нужна
    1.10
     треба
    0.99
     нужен
    0.99
     genannt
    0.99
     treba
    0.98
     সবই
    0.97
    使う
    0.96
    があります
    0.94
    это
    0.94
    POSITIVE LOGITS
     during
    2.20
    During
    2.13
     after
    2.11
     During
    2.08
     throughout
    2.02
    After
    1.95
    during
    1.94
     while
    1.87
     After
    1.87
     durante
    1.84
    Act Density 1.503%

    No Known Activations