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

    Neuronpedia

    INDEX
    Explanations

    spaceship or arena locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lax
    0.39
    ɫ
    0.39
    terna
    0.37
     Pum
    0.36
     va
    0.36
    栄
    0.35
     Geg
    0.34
     टक्कर
    0.34
     Le
    0.34
     grocery
    0.34
    POSITIVE LOGITS
    Herd
    0.42
     बिफोर
    0.42
     ஆய்
    0.42
    Calls
    0.41
     syncing
    0.41
    Callbacks
    0.40
    وفي
    0.40
     एक्सरसाइज
    0.39
     माहिती
    0.39
    ईडी
    0.39
    Act Density 0.000%

    No Known Activations