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

    Neuronpedia

    INDEX
    Explanations

    't / <start_of_turn>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isoforms
    0.17
     учетом
    0.17
     substit
    0.17
    ೪
    0.16
     substituents
    0.16
    證據
    0.16
     norepinephrine
    0.16
    併
    0.16
     ஆதார
    0.15
     perturbation
    0.15
    POSITIVE LOGITS
    ك
    0.22
    این
    0.19
    اول
    0.19
    K
    0.18
    كتب
    0.18
    U
    0.17
    اي
    0.17
    ch
    0.17
    m
    0.16
    H
    0.16
    Act Density 7.336%

    No Known Activations