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

    Neuronpedia

    INDEX
    Explanations

    structured agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.09
     영
    1.06
    兩
    1.04
     the
    1.03
     신
    1.01
     all
    0.98
     ETFs
    0.97
     без
    0.97
     а
    0.97
     한
    0.96
    POSITIVE LOGITS
    ysis
    1.21
    urel
    1.20
    ermanfaat
    1.15
     kwietnia
    1.14
    lamiento
    1.13
     juin
    1.12
     Theorem
    1.12
    uls
    1.12
     juillet
    1.11
     zakres
    1.11
    Act Density 0.048%

    No Known Activations