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

    Neuronpedia

    INDEX
    Explanations

    JSON structure examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     route
    0.42
     navigate
    0.41
    atakse
    0.41
     sector
    0.39
     window
    0.38
     luna
    0.38
     fok
    0.38
     रूट्स
    0.38
     Hog
    0.37
     caller
    0.37
    POSITIVE LOGITS
       
    0.57
    VPN
    0.43
    Ссы
    0.40
    冒
    0.38
     ชี
    0.37
    ୃ
    0.37
    WebService
    0.36
    LaunchAction
    0.36
    AnalyzeAction
    0.35
     стекло
    0.34
    Act Density 0.005%

    No Known Activations