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

    Neuronpedia

    INDEX
    Explanations

    by-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     именем
    0.84
     रूपये
    0.78
    HCl
    0.72
     प्रच
    0.72
     शायरी
    0.72
     sleeveless
    0.71
     DJs
    0.70
    ⵏ
    0.70
     cufflinks
    0.69
     ხელისუფლების
    0.69
    POSITIVE LOGITS
     conclusions
    0.69
    役割
    0.61
    ொரு
    0.60
     Risks
    0.58
    각
    0.57
     Interests
    0.57
     Technical
    0.57
     područ
    0.56
     های
    0.56
     נו
    0.56
    Act Density 0.116%

    No Known Activations