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

    Neuronpedia

    INDEX
    Explanations

    data structures, files, and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strCmd
    0.46
     exercitation
    0.46
    CU
    0.45
     NITRO
    0.45
     тільки
    0.45
    צר
    0.43
    cY
    0.43
    oliko
    0.42
    ческого
    0.42
    Pieces
    0.41
    POSITIVE LOGITS
     House
    0.55
     Associates
    0.50
     sombre
    0.49
     Dance
    0.46
     During
    0.46
     Defence
    0.45
     Hospital
    0.45
     Log
    0.45
     Fish
    0.45
     Foot
    0.44
    Act Density 0.003%

    No Known Activations