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

    Neuronpedia

    INDEX
    Explanations

    first step in recognizing thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anwendungen
    0.96
    Computational
    0.87
     صارفین
    0.86
    Compiler
    0.86
     Computational
    0.85
    Users
    0.83
     пользователей
    0.83
    Graphical
    0.82
    的用户
    0.81
    应用程序
    0.81
    POSITIVE LOGITS
     ego
    0.99
     empat
    0.95
     hurt
    0.90
     nuanced
    0.87
     vaso
    0.85
     empathetic
    0.85
     egos
    0.84
     Teflon
    0.84
     reactive
    0.84
     peac
    0.83
    Act Density 0.469%

    No Known Activations