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

    Neuronpedia

    INDEX
    Explanations

    life within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cytokinin
    0.39
     muon
    0.37
     puffs
    0.37
     reactants
    0.37
     nếu
    0.36
     হালকা
    0.36
     επίσης
    0.36
     "?"
    0.36
    按钮
    0.36
     docking
    0.35
    POSITIVE LOGITS
    हम
    0.41
     brutally
    0.40
     nosso
    0.39
     vanqu
    0.39
     nuestros
    0.38
     vergang
    0.37
     nossa
    0.37
     nuestra
    0.37
     nuestras
    0.36
     வரலாறு
    0.36
    Act Density 0.462%

    No Known Activations