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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rául
    1.11
    <unused59>
    1.10
    oruč
    1.09
    ﹟
    1.07
    нены
    1.07
    ramique
    1.04
     Heming
    1.03
    утбу
    1.03
    ][/
    1.03
    ėj
    1.02
    POSITIVE LOGITS
    t
    0.95
    as
    0.90
    in
    0.88
     absolutely
    0.84
     and
    0.82
     directly
    0.81
     all
    0.80
     chaperone
    0.79
     one
    0.79
     potentially
    0.77
    Act Density 0.080%

    No Known Activations