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

    Neuronpedia

    INDEX
    Explanations

    make stronger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    采用了
    0.40
    采用
    0.37
     рассматривать
    0.36
    وص
    0.35
     adopts
    0.35
     вышла
    0.34
     desarrollada
    0.34
     quedando
    0.34
     unteren
    0.32
     analizar
    0.32
    POSITIVE LOGITS
     give
    0.66
     strengthen
    0.61
     heighten
    0.60
     boost
    0.59
     enhance
    0.59
     amplify
    0.57
     bolster
    0.57
     make
    0.55
     improve
    0.55
     empower
    0.54
    Act Density 0.561%

    No Known Activations