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

    Neuronpedia

    INDEX
    Explanations

    illegal, consequences, world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inisc
    0.43
    anea
    0.42
    dauer
    0.42
    uki
    0.38
    agas
    0.38
    ূট
    0.37
    ബാ
    0.37
    ok
    0.37
    swith
    0.37
    anken
    0.37
    POSITIVE LOGITS
     Maradona
    0.45
     decommissioning
    0.43
     retra
    0.42
     watchdog
    0.41
     Raila
    0.41
    шив
    0.41
     уда
    0.41
    និ
    0.40
     इंदिरा
    0.40
    ირ
    0.40
    Act Density 0.001%

    No Known Activations