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

    Neuronpedia

    INDEX
    Explanations

    alternative uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нулю
    0.69
    消毒
    0.66
    Deadline
    0.65
     imperme
    0.65
     emeritus
    0.64
    safety
    0.63
     нега
    0.63
    ancellationToken
    0.63
    Offline
    0.63
     безопасность
    0.63
    POSITIVE LOGITS
     multilingual
    0.86
     superstructure
    0.79
     franchise
    0.73
     Marxist
    0.72
     multiplets
    0.71
     franchises
    0.71
     각종
    0.71
     factions
    0.70
     ProductName
    0.70
     franchising
    0.70
    Act Density 0.669%

    No Known Activations