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

    Neuronpedia

    INDEX
    Explanations

    states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    とその
    0.39
    Voilà
    0.38
     an
    0.38
     a
    0.36
     हमारा
    0.35
     किसका
    0.35
    '
    0.35
    及其
    0.34
    并在
    0.34
    ’
    0.34
    POSITIVE LOGITS
     galore
    0.47
     abound
    0.46
    গুলি
    0.39
    াতাড়ি
    0.38
    ները
    0.37
     vannak
    0.37
     soared
    0.36
     are
    0.35
    が高
    0.35
     plentiful
    0.35
    Act Density 0.144%

    No Known Activations