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

    Neuronpedia

    INDEX
    Explanations

    wear gloves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    并未
    0.49
    Incorrect
    0.43
    edLeft
    0.43
    についての
    0.41
    ('',
    0.41
     экономических
    0.41
    カスタ
    0.40
     (!(
    0.40
     измени
    0.40
     виправи
    0.40
    POSITIVE LOGITS
     tarp
    0.67
     idiots
    0.64
     bungee
    0.59
     pissed
    0.59
     compressor
    0.57
     drywall
    0.57
     idiot
    0.56
     carbide
    0.55
     winch
    0.55
     VHF
    0.55
    Act Density 0.017%

    No Known Activations