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

    Neuronpedia

    INDEX
    Explanations

    Faction, clan, rumours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    美国
    1.13
    ⤴
    1.12
    🅰
    1.10
    🎾
    1.10
    🆒
    1.10
     американ
    1.10
    ⚾
    1.08
     inappropri
    1.08
    🙆
    1.08
    odynamic
    1.07
    POSITIVE LOGITS
    Faction
    1.24
    Clan
    1.13
     rumour
    1.10
     rumors
    1.09
     Clan
    1.08
     rumor
    1.02
    噂
    1.01
     patrols
    1.00
     clans
    0.99
     rumours
    0.98
    Act Density 0.159%

    No Known Activations