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

    Neuronpedia

    INDEX
    Explanations

    roleplay instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bibliography
    1.06
     tyrant
    1.01
     printer
    0.97
     univers
    0.96
     turmeric
    0.94
     antivirus
    0.93
     finalist
    0.92
     arbitration
    0.92
     witchcraft
    0.91
     multiverse
    0.91
    POSITIVE LOGITS
     viewpoints
    0.69
     accedi
    0.65
     beamed
    0.64
     Everyday
    0.64
     Attitudes
    0.63
     viewpoint
    0.63
     View
    0.63
     Speaks
    0.63
    loff
    0.62
     обстанов
    0.60
    Act Density 0.178%

    No Known Activations