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

    Neuronpedia

    INDEX
    Explanations

    environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weap
    0.52
     показывает
    0.52
    chromiumfx
    0.52
     monstru
    0.51
     vutto
    0.51
     можли
    0.50
    analisi
    0.50
     biopsies
    0.49
     бом
    0.49
     позд
    0.49
    POSITIVE LOGITS
     Environments
    0.84
     Environment
    0.83
     environment
    0.80
     환경
    0.77
    環境
    0.75
     محیط
    0.74
    environment
    0.73
     environments
    0.73
     Environmental
    0.72
     environmental
    0.72
    Act Density 0.031%

    No Known Activations