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

    Neuronpedia

    INDEX
    Explanations

    yesterday, blob name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Brew
    0.44
    Build
    0.41
    store
    0.41
    Walk
    0.41
    Busy
    0.41
    最小
    0.40
    Taiwan
    0.40
    Conn
    0.40
    '?
    0.40
    kiem
    0.39
    POSITIVE LOGITS
     Fr
    0.40
     poh
    0.39
    ructural
    0.38
     faith
    0.38
     quar
    0.38
     mas
    0.38
     Emp
    0.38
    мп
    0.37
     transverse
    0.37
    грамма
    0.37
    Act Density 0.004%

    No Known Activations