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

    Neuronpedia

    INDEX
    Explanations

    first names followed by names/titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dogma
    0.22
     orthodoxy
    0.22
    asmuch
    0.21
     glomer
    0.20
     sinister
    0.20
     impoverished
    0.20
     elytra
    0.20
    ஸ்ட்
    0.20
    バイト
    0.20
     aloof
    0.20
    POSITIVE LOGITS
    ↵
    0.22
     ಹಾಗೂ
    0.21
     Chris
    0.20
     ও
    0.20
     personalizada
    0.20
     senare
    0.19
     एवं
    0.19
     disbursements
    0.17
     contará
    0.17
     digitally
    0.17
    Act Density 0.041%

    No Known Activations