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

    Neuronpedia

    INDEX
    Explanations

    whiskers made of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    impresa
    1.37
     îl
    1.33
    鉅
    1.28
    จุ
    1.24
     entrambi
    1.21
    lysis
    1.20
     งวด
    1.19
    钜
    1.18
    ungannya
    1.17
    一行
    1.16
    POSITIVE LOGITS
     WiFi
    3.11
     wifi
    3.10
     Wifi
    3.08
    Wifi
    2.94
     ambient
    2.83
    座椅
    2.82
    WiFi
    2.80
     WIFI
    2.77
     WLAN
    2.72
     HVAC
    2.67
    Act Density 0.503%

    No Known Activations