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

    Neuronpedia

    INDEX
    Explanations

    missing or incomplete states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.38
    ми
    0.36
    e
    0.36
    8
    0.35
    ৬
    0.35
    the
    0.34
    iid
    0.34
    time
    0.33
    The
    0.33
    where
    0.32
    POSITIVE LOGITS
     a
    0.51
     on
    0.51
     was
    0.47
     to
    0.45
     one
    0.43
     an
    0.43
     it
    0.42
     be
    0.40
     out
    0.36
     of
    0.34
    Act Density 0.581%

    No Known Activations