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

    Neuronpedia

    INDEX
    Explanations

    sea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ции
    1.17
    ция
    1.08
    ем
    1.05
     cardí
    1.05
     формат
    0.97
    י
    0.97
    ير
    0.95
     дов
    0.95
    ى
    0.92
    цию
    0.91
    POSITIVE LOGITS
     sea
    1.32
    Sea
    1.26
     Sea
    1.23
    h
    1.16
    AL
    1.01
    sea
    0.98
    <0x98>
    0.96
    ow
    0.93
    fl
    0.92
    art
    0.91
    Act Density 0.013%

    No Known Activations