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

    Neuronpedia

    INDEX
    Explanations

    run function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘭
    0.50
    ՞
    0.48
    ামত
    0.47
     ລັບ
    0.47
     ជា
    0.47
    скоре
    0.46
    naph
    0.46
    ockey
    0.46
    抹茶
    0.46
    cG
    0.45
    POSITIVE LOGITS
    یت
    0.43
     do
    0.40
    run
    0.40
     run
    0.39
    U
    0.39
    ètres
    0.38
     Run
    0.36
     Hob
    0.36
     Jor
    0.36
     Boots
    0.36
    Act Density 0.003%

    No Known Activations