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

    Neuronpedia

    INDEX
    Explanations

    anti- followed by warfare types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keychain
    0.43
     perifer
    0.41
    츨
    0.41
     सेफ्टी
    0.41
    competitive
    0.40
     уйнау
    0.40
    clidean
    0.39
     slam
    0.39
     competitive
    0.39
     безпе
    0.39
    POSITIVE LOGITS
     aircraft
    0.63
     Aircraft
    0.61
    Aircraft
    0.60
    aircraft
    0.58
     tank
    0.55
     Tank
    0.54
     submarine
    0.54
     ship
    0.52
    tank
    0.52
    Tank
    0.50
    Act Density 0.002%

    No Known Activations