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

    Neuronpedia

    INDEX
    Explanations

    canning and food preservation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entreg
    0.47
     smuggled
    0.47
     entourage
    0.43
     segit
    0.42
    ibia
    0.40
    施術
    0.40
     crumbled
    0.39
     sprinkled
    0.39
     entangled
    0.39
     XOR
    0.38
    POSITIVE LOGITS
     canning
    1.30
     Canning
    0.88
     preserves
    0.87
     canned
    0.87
     preservation
    0.78
     preserve
    0.78
    preserve
    0.77
     preserved
    0.71
    preserved
    0.71
     preserving
    0.70
    Act Density 0.022%

    No Known Activations