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

    Neuronpedia

    INDEX
    Explanations

    cryptic journal entries and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     printable
    1.11
    Printing
    1.04
     Printable
    1.03
     Printing
    0.95
     documental
    0.95
     Paper
    0.94
     printing
    0.94
    printable
    0.93
     Papier
    0.93
    papier
    0.91
    POSITIVE LOGITS
     entry
    0.95
     entries
    0.95
     equations
    0.94
     paranoid
    0.90
     calculations
    0.89
     predictions
    0.86
     circled
    0.84
     rant
    0.82
     paranoia
    0.81
     incoherent
    0.80
    Act Density 0.037%

    No Known Activations