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

    Neuronpedia

    INDEX
    Explanations

    collaboration and teamwork

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    θυν
    0.89
    th
    0.88
     upas
    0.87
    backdrop
    0.86
    在一起
    0.86
     caval
    0.85
    ತಕ್ಕ
    0.85
     باتوں
    0.84
    特典
    0.83
    mog
    0.82
    POSITIVE LOGITS
    作業
    1.09
    л
    1.09
     çalış
    1.03
    ಜ
    1.02
    𝘰
    1.01
     workpiece
    1.00
     colabor
    1.00
    arbeit
    1.00
     humains
    0.99
     сотрудни
    0.99
    Act Density 0.068%

    No Known Activations