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

    Neuronpedia

    INDEX
    Explanations

    financial feasibility and mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Philippines
    0.42
    Philippines
    0.40
     Scholars
    0.40
     scholars
    0.40
     ফিল
    0.39
     রাজশাহী
    0.39
     scientists
    0.39
     বাংলাদেশ
    0.39
    椙
    0.38
    Scientists
    0.38
    POSITIVE LOGITS
     patching
    0.40
    hoppers
    0.38
    మారు
    0.37
    折り
    0.36
     yur
    0.36
    kwargs
    0.34
     stitch
    0.34
    żu
    0.34
     folding
    0.34
     conversaciones
    0.34
    Act Density 0.002%

    No Known Activations