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

    Neuronpedia

    INDEX
    Explanations

    disk-related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Raster
    0.42
    avatth
    0.38
    فاض
    0.38
    મારી
    0.38
    utely
    0.37
    管理局
    0.37
     soup
    0.37
     gaz
    0.36
     cellulaire
    0.36
     strands
    0.35
    POSITIVE LOGITS
     disk
    0.79
    disk
    0.78
     disks
    0.75
     Disk
    0.75
     диск
    0.75
    Disk
    0.74
     discs
    0.71
     fs
    0.63
     डिस्क
    0.63
     диску
    0.63
    Act Density 0.079%

    No Known Activations