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

    Neuronpedia

    INDEX
    Explanations

    -tion, -ity, and -ing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.24
    AR
    0.79
    AN
    0.78
    I
    0.77
    IN
    0.74
    l
    0.71
    Is
    0.70
    에서는
    0.70
    AT
    0.68
    AG
    0.68
    POSITIVE LOGITS
     and
    1.55
     be
    1.41
     or
    1.30
     are
    1.28
    σ
    1.22
    and
    1.21
     were
    1.14
    ud
    1.12
    us
    1.11
     can
    1.11
    Act Density 2.036%

    No Known Activations