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

    Neuronpedia

    INDEX
    Explanations

    places and circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ses
    -0.10
    that
    -0.09
    the
    -0.09
     rằng
    -0.09
    ingly
    -0.09
    ories
    -0.09
    iyel
    -0.09
    then
    -0.09
    çak
    -0.09
     Trick
    -0.08
    POSITIVE LOGITS
    ver
    0.18
    ever
    0.16
    fore
    0.16
     else
    0.16
    from
    0.15
    of
    0.14
    upon
    0.14
    apon
    0.12
    -ever
    0.12
    on
    0.12
    Act Density 0.043%

    No Known Activations