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

    Neuronpedia

    INDEX
    Explanations

    Flow, spin, rotate, planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overboard
    0.99
    लिस
    0.90
    اوز
    0.90
    ंपल
    0.88
    対
    0.87
     overkill
    0.85
    ientos
    0.85
     dugg
    0.84
    arkeit
    0.83
    证券
    0.83
    POSITIVE LOGITS
    注意
    1.05
    subsection
    1.04
    زى
    1.03
    চে
    1.03
     montaña
    0.99
    mund
    0.99
    دان
    0.96
     पोस्टर
    0.95
    here
    0.95
     সেসব
    0.94
    Act Density 0.000%

    No Known Activations