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

    Neuronpedia

    INDEX
    Explanations

    Intel Core, hardcore, en_core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     core
    0.66
    核心
    0.60
     cores
    0.55
     kernel
    0.52
     fundamental
    0.52
     фундамента
    0.52
    コア
    0.51
    heart
    0.50
     fundamentals
    0.49
     roots
    0.48
    POSITIVE LOGITS
    ore
    0.54
     Corre
    0.53
    Кор
    0.48
     ore
    0.47
    Cor
    0.47
    orea
    0.46
     Kore
    0.45
     Cor
    0.44
     Corinthians
    0.43
     Kor
    0.41
    Act Density 0.012%

    No Known Activations