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

    Neuronpedia

    INDEX
    Explanations

    language, words, and sentence structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    maximum
    0.47
    primary
    0.46
    ipas
    0.46
    polynomial
    0.46
    𝗶
    0.42
     Stabilization
    0.42
     paucity
    0.42
    ut
    0.42
    processors
    0.42
     polled
    0.42
    POSITIVE LOGITS
     zile
    0.51
     colegas
    0.48
     envis
    0.47
     renewables
    0.47
     Até
    0.47
     ecosystem
    0.46
     vilka
    0.46
     foto
    0.45
     escuch
    0.45
     ál
    0.45
    Act Density 0.011%

    No Known Activations