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

    Neuronpedia

    INDEX
    Explanations

    expecting situations or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.88
    /
    0.87
     (
    0.84
     and
    0.80
    -
    0.77
    :
    0.77
    es
    0.77
     in
    0.76
    ies
    0.75
    (
    0.75
    POSITIVE LOGITS
    <unused268>
    1.11
    <unused378>
    1.09
     retShape
    1.09
    <unused1064>
    1.09
    呵呵
    1.09
     decoração
    1.08
    <unused1041>
    1.07
    <unused456>
    1.07
    )$}
    1.06
    <unused946>
    1.05
    Act Density 0.000%

    No Known Activations