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

    Neuronpedia

    INDEX
    Explanations

    differently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    0.75
    தைப்
    0.75
    бри
    0.69
    什么的
    0.64
    वरील
    0.63
    昙
    0.62
    ত্র
    0.62
     suivants
    0.61
    격을
    0.61
    クター
    0.60
    POSITIVE LOGITS
     Differ
    0.93
     einfacher
    0.81
     opposit
    0.79
     founded
    0.79
     sweeter
    0.77
     jinak
    0.75
     differently
    0.75
     চুপ
    0.74
     verbose
    0.73
    Differ
    0.72
    Act Density 0.007%

    No Known Activations